minor (core): updates DEFAULT_BAD_CHARS

Reviewed-on: #9

Dockerfile

@@ -1,57 +0,0 @@
-FROM python:3.13-slim
-
-# Install FFmpeg and dependencies required for gosu installation
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-        ffmpeg \
-        ca-certificates \
-        wget \
-        gnupg \
-        dirmngr \
-        gnupg-agent && \
-    apt-get clean && \
-    rm -rf /var/lib/apt/lists/*
-
-# Install gosu (lightweight tool for dropping privileges)
-RUN set -eux; \
-    dpkgArch="$(dpkg --print-architecture | awk -F- '{ print $NF }')"; \
-    wget -O /usr/local/bin/gosu "https://github.com/tianon/gosu/releases/download/1.17/gosu-$dpkgArch"; \
-    wget -O /usr/local/bin/gosu.asc "https://github.com/tianon/gosu/releases/download/1.17/gosu-$dpkgArch.asc"; \
-    export GNUPGHOME="$(mktemp -d)"; \
-    gpg --batch --keyserver hkps://keys.openpgp.org --recv-keys B42F6819007F00F88E364FD4036A9C25BF357DD4; \
-    gpg --batch --verify /usr/local/bin/gosu.asc /usr/local/bin/gosu; \
-    gpgconf --kill all; \
-    rm -rf "$GNUPGHOME" /usr/local/bin/gosu.asc; \
-    chmod +x /usr/local/bin/gosu; \
-    gosu --version
-
-# Set Python environment variables
-ENV PYTHONDONTWRITEBYTECODE=1 \
-    PYTHONUNBUFFERED=1
-
-# Set working directory
-WORKDIR /app
-
-# Copy package metadata and source code
-COPY setup.py pyproject.toml README.md ./
-COPY audio_splitter/ ./audio_splitter/
-
-# Install the package
-RUN pip install --no-cache-dir .
-
-# Create a non-root user with UID 1000
-RUN addgroup --system --gid 1000 appgroup && \
-    adduser --system --uid 1000 --ingroup appgroup appuser
-
-# Change ownership of /app to the container user (so it can write there if needed)
-RUN chown -R appuser:appgroup /app
-
-# Copy the entrypoint script
-COPY docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
-RUN chmod +x /usr/local/bin/docker-entrypoint.sh
-
-# Set the entrypoint
-ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]
-
-# Default command (shows help if no arguments provided)
-CMD ["--help"]

audio_splitter/constants.py

@@ -1,20 +1,124 @@
-"""Global constants and default values."""
+# audio_splitter/constants.py
+"""Global constants for the audio splitter.
 
-# Mapping from user‑friendly format names to FFmpeg format identifiers,
-# file extensions, and whether the container is audio‑only.
-FORMAT_INFO = {
-    'mp3':      {'ffmpeg': 'mp3',      'ext': '.mp3',  'audio_only': True},
-    'm4a':      {'ffmpeg': 'mp4',      'ext': '.m4a',  'audio_only': True},
-    'mp4':      {'ffmpeg': 'mp4',      'ext': '.mp4',  'audio_only': False},
-    'mkv':      {'ffmpeg': 'matroska', 'ext': '.mkv',  'audio_only': False},
-    'matroska': {'ffmpeg': 'matroska', 'ext': '.mkv',  'audio_only': False},
-    'ogg':      {'ffmpeg': 'ogg',      'ext': '.ogg',  'audio_only': True},
-    'opus':     {'ffmpeg': 'ogg',      'ext': '.opus', 'audio_only': True},
-    'flac':     {'ffmpeg': 'flac',     'ext': '.flac', 'audio_only': True},
-    'wav':      {'ffmpeg': 'wav',      'ext': '.wav',  'audio_only': True},
-    'aac':      {'ffmpeg': 'adts',     'ext': '.aac',  'audio_only': True},
+This file serves as the single source of truth for:
+- Container formats and their properties
+- Audio codecs and their recommended containers
+- Video codec support per container
+- File extensions for each codec/container combination
+- Compatibility matrix for codec/container validation
+
+Codec != Container != File Extension.
+Example: Opus (codec) → Ogg (container) → .opus (extension)
+"""
+from typing import Dict, Optional
+
+# ------------------------------------------------------------------------------
+# Container information
+# ------------------------------------------------------------------------------
+CONTAINER_INFO = [
+    # Audio-only containers
+    {'name': 'mp3', 'ffmpeg': 'mp3', 'extension': '.mp3', 'supports_video': True, 'supports_subs': False},
+    {'name': 'm4a', 'ffmpeg': 'mp4', 'extension': '.m4a', 'supports_video': False, 'supports_subs': False},
+    {'name': 'flac', 'ffmpeg': 'flac', 'extension': '.flac', 'supports_video': False, 'supports_subs': False},
+    {'name': 'wav', 'ffmpeg': 'wav', 'extension': '.wav', 'supports_video': False, 'supports_subs': False},
+    {'name': 'aac', 'ffmpeg': 'adts', 'extension': '.aac', 'supports_video': False, 'supports_subs': False},
+    # Containers that support video and subtitles
+    {'name': 'mp4', 'ffmpeg': 'mp4', 'extension': '.mp4', 'supports_video': True, 'supports_subs': True},
+    {'name': 'mkv', 'ffmpeg': 'matroska', 'extension': '.mkv', 'supports_video': True, 'supports_subs': True},
+    {'name': 'ogg', 'ffmpeg': 'ogg', 'extension': '.ogg', 'supports_video': True, 'supports_subs': True},
+    {'name': 'webm', 'ffmpeg': 'webm', 'extension': '.webm', 'supports_video': True, 'supports_subs': False},
+]
+
+# Container name lookup set for fast membership checks
+CONTAINER_NAMES = {container['name'] for container in CONTAINER_INFO}
+
+
+def get_container_info(container_name: str) -> Optional[Dict]:
+    """Return container info dict or None if not found."""
+    for container in CONTAINER_INFO:
+        if container['name'] == container_name:
+            return container
+    return None
+
+
+# ------------------------------------------------------------------------------
+# Codec information
+# ------------------------------------------------------------------------------
+CODEC_INFO = [
+    # Audio codecs
+    {'name': 'opus', 'ffmpeg': 'libopus', 'recommended_container': 'ogg', 'recommended_extension': '.opus', 'codec_type': 'audio'},
+    {'name': 'vorbis', 'ffmpeg': 'libvorbis', 'recommended_container': 'ogg', 'recommended_extension': '.ogg', 'codec_type': 'audio'},
+    {'name': 'flac', 'ffmpeg': 'flac', 'recommended_container': 'flac', 'recommended_extension': '.flac', 'codec_type': 'audio'},
+    {'name': 'aac', 'ffmpeg': 'aac', 'recommended_container': 'mp4', 'recommended_extension': '.m4a', 'codec_type': 'audio'},
+    {'name': 'mp3', 'ffmpeg': 'libmp3lame', 'recommended_container': 'mp3', 'recommended_extension': '.mp3', 'codec_type': 'audio'},
+    {'name': 'alac', 'ffmpeg': 'alac', 'recommended_container': 'mp4', 'recommended_extension': '.m4a', 'codec_type': 'audio'},
+    {'name': 'pcm_s16le', 'ffmpeg': 'pcm_s16le', 'recommended_container': 'wav', 'recommended_extension': '.wav', 'codec_type': 'audio'},
+    # Video codecs (including cover images)
+    {'name': 'theora', 'ffmpeg': 'libtheora', 'recommended_container': 'ogg', 'recommended_extension': '.ogv', 'codec_type': 'video'},
+    {'name': 'vp8', 'ffmpeg': 'libvpx', 'recommended_container': 'webm', 'recommended_extension': '.webm', 'codec_type': 'video'},
+    {'name': 'vp9', 'ffmpeg': 'libvpx-vp9', 'recommended_container': 'webm', 'recommended_extension': '.webm', 'codec_type': 'video'},
+    {'name': 'av1', 'ffmpeg': 'libaom-av1', 'recommended_container': 'mkv', 'recommended_extension': '.mkv', 'codec_type': 'video'},
+    {'name': 'h264', 'ffmpeg': 'libx264', 'recommended_container': 'mp4', 'recommended_extension': '.mp4', 'codec_type': 'video'},
+    {'name': 'h265', 'ffmpeg': 'libx265', 'recommended_container': 'mp4', 'recommended_extension': '.mp4', 'codec_type': 'video'},
+    {'name': 'png', 'ffmpeg': 'png', 'recommended_container': 'ogg', 'recommended_extension': '.png', 'codec_type': 'video'},
+    {'name': 'mjpeg', 'ffmpeg': 'mjpeg', 'recommended_container': 'ogg', 'recommended_extension': '.jpg', 'codec_type': 'video'},
+    # Subtitle codecs
+    {'name': 'srt', 'ffmpeg': 'srt', 'recommended_container': 'mkv', 'recommended_extension': '.srt', 'codec_type': 'subtitle'},
+    {'name': 'ass', 'ffmpeg': 'ass', 'recommended_container': 'mkv', 'recommended_extension': '.ass', 'codec_type': 'subtitle'},
+    {'name': 'vtt', 'ffmpeg': 'webvtt', 'recommended_container': 'webm', 'recommended_extension': '.vtt', 'codec_type': 'subtitle'},
+]
+
+# Map codec name → recommended container
+CODEC_TO_CONTAINER_MAP = {codec['name']: codec['recommended_container'] for codec in CODEC_INFO}
+CODEC_TO_EXTENSION_MAP = {codec['name']: codec['recommended_extension'] for codec in CODEC_INFO}
+
+# Map codec name → FFmpeg encoder name
+CODEC_NAME_TO_FFMPEG = {codec['name']: codec['ffmpeg'] for codec in CODEC_INFO}
+
+# ------------------------------------------------------------------------------
+# Compatibility matrix: container → supported audio and video codecs
+# ------------------------------------------------------------------------------
+# Each container entry maps to a dict with 'audio' and 'video' keys.
+# - 'audio': list of audio codec names that are supported in this container.
+#            Use None to indicate that any audio codec is supported.
+# - 'video': list of video codec names that are supported in this container.
+#            Use None to indicate that any video codec is supported.
+#            Empty list means no video support (audio-only container).
+COMPATIBILITY_MATRIX = {
+    'mp3': {'audio': ['mp3'], 'video': ['png', 'mjpeg']},
+    'm4a': {'audio': ['aac', 'alac', 'opus', 'flac'], 'video': []},
+    'mp4': {'audio': ['aac', 'alac', 'opus', 'flac', 'mp3'], 'video': ['h264', 'h265', 'vp9', 'av1']},
+    'mkv': {'audio': None, 'video': None},
+    'ogg': {'audio': ['opus', 'vorbis', 'flac'], 'video': ['theora', 'vp8', 'png', 'mjpeg']},
+    'webm': {'audio': ['opus', 'vorbis'], 'video': ['vp8', 'vp9', 'av1']},
+    'flac': {'audio': ['flac'], 'video': ['png', 'mjpeg']},
+    'wav': {'audio': ['pcm_s16le'], 'video': []},
+    'aac': {'audio': ['aac'], 'video': []},
 }
 
-# Default characters to replace when --replace-bad-chars is enabled.
-# Includes common punctuation, single quote, and a trailing space.
-DEFAULT_BAD_CHARS = r',!@#№$;:%^&?*(){}[]\/<>+=~`\' '
+# ------------------------------------------------------------------------------
+# Helper functions for compatibility checking
+# ------------------------------------------------------------------------------
+def is_audio_codec_supported(container: str, audio_codec: str) -> bool:
+    """Check if an audio codec is supported in the given container."""
+    entry = COMPATIBILITY_MATRIX.get(container, {})
+    supported = entry.get('audio')
+    if supported is None:
+        return True
+    return audio_codec in supported
+
+
+def is_video_codec_supported(container: str, video_codec: str) -> bool:
+    """Check if a video codec is supported in the given container."""
+    entry = COMPATIBILITY_MATRIX.get(container, {})
+    supported = entry.get('video')
+    if supported is None:
+        return True
+    return video_codec in supported
+
+
+# ------------------------------------------------------------------------------
+# Default bad characters (for filename sanitization)
+# ------------------------------------------------------------------------------
+DEFAULT_BAD_CHARS = r'!@#№$;:%^&?*(){}[]\/<>+=~`\'|," '

audio_splitter/core.py

@@ -1,30 +1,69 @@
-"""Core logic: orchestrates the splitting process."""
+# audio_splitter/core.py
+"""Core splitting logic – orchestrates the entire split process."""
 
 import os
 import subprocess
+import sys
+from typing import List, Dict, Any
 
-from .constants import FORMAT_INFO
-from .ffmpeg import get_audio_duration, get_stream_info, get_metadata, build_ffmpeg_command
-from .formats import determine_output_format, validate_format_compatibility
+from .constants import (
+    CONTAINER_NAMES,
+    CODEC_TO_EXTENSION_MAP,
+    CODEC_NAME_TO_FFMPEG,
+)
+from .ffmpeg import (
+    get_audio_duration,
+    get_stream_info,
+    get_metadata,
+    build_ffmpeg_command,
+    is_attached_picture,
+    extract_cover_image,
+)
+from .formats import (
+    determine_output_format,
+    validate_format_compatibility,
+)
+from .handlers import get_handler, needs_drop_video
 from .timestamp import parse_track_timestamps, resolve_end_times
 from .filename import build_filename
 from .metadata import build_metadata_dict
 from .utils import format_time
 
 
-def split_audio(input_file, output_directory, tracks, args):
+def split_audio(input_file: str, output_directory: str, tracks: List[Dict[str, Any]], args) -> None:
     """
     Main orchestration function: split the audio file into tracks.
 
     Args:
         input_file: Path to the input media file.
         output_directory: Directory where output files will be saved.
-        tracks: List of dicts, each containing parsed fields.
-        args: Parsed command‑line arguments (namespace).
+        tracks: List of dicts, each containing parsed fields (ts, tn, an, ...).
+        args: Parsed command‑line arguments (namespace) with attributes:
+            - container: output container name (or None for auto-detect)
+            - audio_codec: audio codec (copy or encoder)
+            - video_codec: video codec (copy or encoder)
+            - subtitle_codec: subtitle codec (copy or encoder)
+            - video_quality: integer or None
+            - drop_video: bool
+            - drop_subs: bool
+            - number_tracks: bool
+            - output_template: str
+            - replace_bad_chars: bool
+            - replacement_char: str
+            - bad_chars: str
+            - skip_existing: bool
+            - album: str or None
+            - comment: str or None
+            - no_comment: bool
+            - comment_stream: int or None
+            - merge_comments: bool
+            - comment_separator: str
+            - delete_original: bool
+            - cover_image: str or None (optional, set by web backend)
 
     Raises:
         RuntimeError: If no audio stream is found.
-        ValueError: If timestamp parsing or format compatibility fails.
+        ValueError: If compatibility validation fails.
     """
     # --------------------------------------------------------------------------
     # 1. Setup
@@ -42,26 +81,59 @@ def split_audio(input_file, output_directory, tracks, args):
         raise RuntimeError("No audio stream found in input file.")
 
     # --------------------------------------------------------------------------
-    # 2. Format decision
+    # 2. Determine output container
     # --------------------------------------------------------------------------
-    output_format = determine_output_format(stream_info, args.format, args.transcode_to, input_file=input_file)
-    print(f"Output container: {output_format}")
-
-    validate_format_compatibility(output_format, stream_info,
-                                  args.drop_video, args.drop_subs)
-
-    # Determine file extension.
-    extension_info = FORMAT_INFO.get(output_format, {})
-    extension = extension_info.get('ext', '.mkv')
+    user_container = getattr(args, 'container', None)
+    output_container = determine_output_format(
+        stream_info,
+        user_format=user_container,
+        transcode_audio=args.audio_codec if args.audio_codec != 'copy' else None,
+        input_file=input_file
+    )
+    print(f"Output container: {output_container}")
 
     # --------------------------------------------------------------------------
-    # 3. Parse timestamps
+    # 3. Validate compatibility
+    # --------------------------------------------------------------------------
+    try:
+        validate_format_compatibility(
+            container=output_container,
+            stream_info=stream_info,
+            drop_video=args.drop_video,
+            drop_subs=args.drop_subs,
+            input_file=input_file,
+            audio_codec=args.audio_codec,
+            video_codec=args.video_codec,
+        )
+    except ValueError as e:
+        raise RuntimeError(f"Compatibility error: {e}")
+
+    # --------------------------------------------------------------------------
+    # 4. Determine output audio codec and extension
+    # --------------------------------------------------------------------------
+    # Determine the audio codec that will be used in the output
+    if args.audio_codec != 'copy':
+        output_audio_codec = args.audio_codec
+    else:
+        output_audio_codec = stream_info.get('audio_codec', '')
+
+    # Choose extension based on audio codec if possible, otherwise fallback to container default
+    if output_audio_codec in CODEC_TO_EXTENSION_MAP:
+        extension = CODEC_TO_EXTENSION_MAP[output_audio_codec]
+    else:
+        container_info = next((c for c in CONTAINER_INFO if c['name'] == output_container), None)
+        extension = container_info['extension'] if container_info else '.mkv'
+
+    print(f"Output extension: {extension}")
+
+    # --------------------------------------------------------------------------
+    # 5. Parse timestamps
     # --------------------------------------------------------------------------
     track_times = parse_track_timestamps(tracks)
     resolved_times = resolve_end_times(track_times, total_duration)
 
     # --------------------------------------------------------------------------
-    # 4. Fetch original metadata (for fallbacks)
+    # 6. Fetch original metadata (for fallbacks)
     # --------------------------------------------------------------------------
     input_metadata = get_metadata(input_file)
     original_album = input_metadata.get('album')
@@ -78,7 +150,30 @@ def split_audio(input_file, output_directory, tracks, args):
             print(f"  Stream {idx}: '{comment}'")
 
     # --------------------------------------------------------------------------
-    # 5. Process each track
+    # 7. Handle attached picture (cover art)
+    # --------------------------------------------------------------------------
+    cover_image_path = getattr(args, 'cover_image', None)
+    if cover_image_path and not os.path.exists(cover_image_path):
+        cover_image_path = None
+
+    if not cover_image_path and not args.drop_video and stream_info.get('has_video'):
+        if is_attached_picture(input_file):
+            cover_image_path = os.path.join(output_directory, 'cover.png')
+            if extract_cover_image(input_file, cover_image_path):
+                print("Extracted cover image for all tracks.")
+            else:
+                cover_image_path = None
+
+    # Check if we need special handling (e.g., Opus files need opustags)
+    input_audio_codec = stream_info.get('audio_codec')
+    cover_handler = get_handler(output_container, input_audio_codec)
+    needs_drop = needs_drop_video(output_container, input_audio_codec)
+    if cover_image_path and needs_drop:
+        print(f"Using special handler for {output_container} + {input_audio_codec}")
+        print("Temporarily dropping video for opustags post-processing.")
+
+    # --------------------------------------------------------------------------
+    # 8. Process each track
     # --------------------------------------------------------------------------
     for idx, track in enumerate(tracks, start=1):
         start_seconds, end_seconds = resolved_times[idx - 1]
@@ -91,31 +186,58 @@ def split_audio(input_file, output_directory, tracks, args):
         track_name = track.get('tn', 'Unknown')
 
         # ----------------------------------------------------------------------
-        # 5a. Build filename
+        # 8a. Build filename
         # ----------------------------------------------------------------------
         clean_filename = build_filename(track, idx, extension, args)
         output_path = os.path.join(output_directory, clean_filename)
 
         # ----------------------------------------------------------------------
-        # 5b. Handle existing files
+        # 8b. Handle existing files
         # ----------------------------------------------------------------------
         if args.skip_existing and os.path.exists(output_path):
             print(f"Skipping track {idx}: {output_path} already exists.")
             continue
 
         # ----------------------------------------------------------------------
-        # 5c. Build metadata
+        # 8c. Build metadata
         # ----------------------------------------------------------------------
         metadata = build_metadata_dict(track, idx, input_metadata, args)
 
         # ----------------------------------------------------------------------
-        # 5d. Build and execute FFmpeg command
+        # 8d. Build and execute FFmpeg command
         # ----------------------------------------------------------------------
+        # Map codec names to FFmpeg encoder names
+        audio_enc = args.audio_codec
+        if audio_enc != 'copy':
+            audio_enc = CODEC_NAME_TO_FFMPEG.get(audio_enc, audio_enc)  # fallback to itself if not found
+        video_enc = args.video_codec
+        if video_enc != 'copy':
+            video_enc = CODEC_NAME_TO_FFMPEG.get(video_enc, video_enc)
+        subtitle_enc = args.subtitle_codec
+        if subtitle_enc != 'copy':
+            subtitle_enc = CODEC_NAME_TO_FFMPEG.get(subtitle_enc, subtitle_enc)
+        
+        # Then build command with these mapped encoders
+        # Use temporary drop_video for handlers that need it
+        effective_drop_video = args.drop_video or (cover_image_path and needs_drop)
+        # For handlers that need opustags post-processing, don't pass cover_image_path
+        # to ffmpeg - it will process audio-only, then handler adds cover afterward
+        ffmpeg_cover_path = None if (cover_image_path and needs_drop) else cover_image_path
         cmd = build_ffmpeg_command(
-            input_file, start_seconds, duration_seconds, output_path,
-            stream_info, output_format, args.transcode_to,
-            args.drop_video, args.drop_subs,
-            metadata=metadata
+            input_file=input_file,
+            start_seconds=start_seconds,
+            duration_seconds=duration_seconds,
+            output_path=output_path,
+            stream_info=stream_info,
+            format_opt=output_container,
+            audio_codec=audio_enc,
+            video_codec=video_enc,
+            subtitle_codec=subtitle_enc,
+            metadata=metadata,
+            cover_image_path=ffmpeg_cover_path,
+            video_quality=getattr(args, 'video_quality', None),
+            drop_video=effective_drop_video,
+            drop_subs=args.drop_subs,
         )
 
         print(f"Extracting track {idx}: {track_name} "
@@ -128,3 +250,28 @@ def split_audio(input_file, output_directory, tracks, args):
             print(result.stderr)
         else:
             print(f"  -> Saved to: {output_path}")
+            # Apply cover image handler if needed
+            if cover_image_path and not args.drop_video and needs_drop:
+                print(f"Applying cover image via {output_container} handler...")
+                if not cover_handler(
+                    input_file=input_file,
+                    cover_image_path=cover_image_path,
+                    output_path=output_path,
+                    stream_info=stream_info,
+                    audio_codec=audio_enc,
+                    video_codec=video_enc,
+                    video_quality=getattr(args, 'video_quality', None),
+                    drop_video=args.drop_video,
+                    drop_subs=args.drop_subs,
+                ):
+                    print(f"Warning: Failed to attach cover image to {output_path}")
+
+    # --------------------------------------------------------------------------
+    # 9. Delete original file if requested
+    # --------------------------------------------------------------------------
+    if getattr(args, 'delete_original', False):
+        try:
+            os.remove(input_file)
+            print(f"Deleted original file: {input_file}")
+        except OSError as e:
+            print(f"Warning: Could not delete original file: {e}")

audio_splitter/defaults.py

@@ -0,0 +1,35 @@
+"""Default values for all configurable options shared between CLI, web backend, and frontend."""
+
+# Output container format (used when user doesn't specify one; auto-detection overrides this)
+DEFAULT_FORMAT = "mp3"
+
+# Filename template
+DEFAULT_OUTPUT_TEMPLATE = "%an-%tn.%ext"
+
+# Character replacement
+DEFAULT_REPLACEMENT_CHAR = "_"
+DEFAULT_BAD_CHARS = r'!@#№$;:%^&?*(){}[]\/<>+=~`\' '
+
+# Tracklist parsing
+DEFAULT_TRACKLIST_FORMAT = "%ts %tn - %an"
+
+# Metadata defaults
+DEFAULT_ALBUM = None
+DEFAULT_COMMENT = None
+DEFAULT_COMMENT_STREAM = None
+DEFAULT_COMMENT_SEPARATOR = "; "
+DEFAULT_NO_COMMENT = False
+DEFAULT_MERGE_COMMENTS = False
+
+# Stream handling
+DEFAULT_DROP_VIDEO = False
+DEFAULT_DROP_SUBS = False
+
+# Filename/export options
+DEFAULT_NUMBER_TRACKS = False
+DEFAULT_REPLACE_BAD_CHARS = True
+DEFAULT_SKIP_EXISTING = False
+DEFAULT_DELETE_ORIGINAL = False
+
+# Transcoding (None means copy codec)
+DEFAULT_TRANSCODE_TO = None

audio_splitter/ffmpeg.py

@@ -1,10 +1,11 @@
-"""FFmpeg/FFprobe interaction utilities for the CLI and web backend."""
+# audio_splitter/ffmpeg.py
+"""FFmpeg/FFprobe interaction utilities."""
 
 import json
 import subprocess
 from typing import Dict, List, Optional, Tuple
 
-from .constants import FORMAT_INFO
+from .constants import CONTAINER_INFO
 from .utils import format_time
 
 
@@ -75,6 +76,28 @@ def get_audio_codec(input_file: str) -> Optional[str]:
     return codec if codec else None
 
 
+def get_video_codec(input_file: str) -> Optional[str]:
+    """
+    Return the codec name of the first video stream.
+
+    Args:
+        input_file: Path to the media file.
+
+    Returns:
+        Codec name as a lowercase string, or None if no video stream exists.
+    """
+    cmd = [
+        'ffprobe', '-v', 'error',
+        '-select_streams', 'v:0',
+        '-show_entries', 'stream=codec_name',
+        '-of', 'default=noprint_wrappers=1:nokey=1',
+        input_file
+    ]
+    result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+    codec = result.stdout.strip().lower()
+    return codec if codec else None
+
+
 def get_stream_info(input_file: str) -> Dict[str, any]:
     """
     Collect information about the streams present in the input file.
@@ -136,7 +159,7 @@ def get_metadata(input_file: str) -> Dict[str, any]:
 
 def get_container_format(input_file: str) -> Optional[str]:
     """
-    Retrieve the container format name (e.g., 'mp4', 'mp3', 'matroska') from the input file.
+    Retrieve the container format name (e.g., 'mp4', 'mp3', 'mkv') from the input file.
 
     Args:
         input_file: Path to the media file.
@@ -156,69 +179,157 @@ def get_container_format(input_file: str) -> Optional[str]:
     format_name = result.stdout.strip().split(',')[0]  # take first if multiple
     if not format_name:
         return None
-    # Normalize common aliases to names used in FORMAT_INFO (container only, not codec-specific)
-    # This mapping is purely for container identification.
+    # Normalize common aliases to names used in CONTAINER_INFO
     mapping = {
-        'mpeg': 'mp3',       # MPEG-1/2 audio (MP3) container
+        'mpeg': 'mp3',
         'mp2': 'mp3',
         'mp4': 'mp4',
-        'm4a': 'mp4',        # M4A is MP4 container
-        'mov': 'mp4',        # QuickTime is MP4-like
+        'm4a': 'mp4',
+        'mov': 'mp4',
         '3gp': 'mp4',
-        'matroska': 'matroska',
-        'webm': 'matroska',  # WebM uses Matroska container
+        'matroska': 'mkv',
+        'webm': 'mkv',
         'ogg': 'ogg',
         'flac': 'flac',
         'wav': 'wav',
         'aac': 'aac',
         'opus': 'opus',
         'mp3': 'mp3',
-        'adts': 'aac',       # raw AAC in ADTS container
-        'amr': 'amr',        # AMR container (rare)
+        'adts': 'aac',
+        'amr': 'amr',
     }
     return mapping.get(format_name, format_name)
 
 
-def build_ffmpeg_command(input_file: str, start_seconds: int, duration_seconds: int,
-                         output_path: str, stream_info: Dict, format_opt: Optional[str],
-                         transcode_audio: Optional[str], drop_video: bool, drop_subs: bool,
-                         metadata: Optional[Dict] = None) -> List[str]:
+def is_attached_picture(input_file: str) -> bool:
     """
-    Construct the FFmpeg command line as a list of arguments.
+    Check if the input file has a video stream that is an attached picture (cover art).
 
-    Args:
-        input_file: Path to the input media file.
-        start_seconds: Start time for the segment (in seconds).
-        duration_seconds: Duration of the segment (in seconds).
-        output_path: Destination path for the output file.
-        stream_info: Dictionary from get_stream_info().
-        format_opt: Output container format (e.g., 'mp3').
-        transcode_audio: Audio codec to transcode to (or None).
-        drop_video: True to remove video streams.
-        drop_subs: True to remove subtitle streams.
-        metadata: Optional dict of metadata key/value pairs to write.
+    Detection logic:
+        1. If there is a video stream with disposition.attached_pic == 1, return True.
+        2. Otherwise, if there is exactly one video stream and its codec is an image
+           format (PNG, MJPEG, JPEG, GIF, BMP), return True.
 
     Returns:
-        A list of command‑line arguments suitable for subprocess.run().
+        True if a cover image is detected, False otherwise.
     """
     cmd = [
-        'ffmpeg',
-        '-i', input_file,
-        '-ss', format_time(start_seconds),
-        '-t', format_time(duration_seconds)
+        'ffprobe', '-v', 'quiet',
+        '-print_format', 'json',
+        '-select_streams', 'v',
+        '-show_entries', 'stream=codec_name,disposition',
+        input_file
     ]
+    result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+    if result.returncode != 0:
+        return False
 
-    # Clear all original metadata.
+    try:
+        data = json.loads(result.stdout)
+        streams = data.get('streams', [])
+        if not streams:
+            return False
+
+        # Check each stream
+        for stream in streams:
+            codec = stream.get('codec_name', '').lower()
+            disposition = stream.get('disposition', {})
+            # If attached_pic is set, it's a cover image
+            if disposition.get('attached_pic') == 1:
+                return True
+            # If not, check if it's an image codec and we have exactly one video stream
+            if codec in ('png', 'mjpeg', 'jpeg', 'gif', 'bmp'):
+                # If there is exactly one video stream, treat it as cover
+                if len(streams) == 1:
+                    return True
+        return False
+    except (json.JSONDecodeError, KeyError):
+        return False
+
+
+def extract_cover_image(input_file: str, output_path: str) -> bool:
+    """
+    Extract the first frame of the video stream (assumed to be an attached picture)
+    and save it to output_path.
+
+    Returns:
+        True if extraction succeeded, False otherwise.
+    """
+    cmd = [
+        'ffmpeg', '-i', input_file,
+        '-map', '0:v:0',
+        '-frames:v', '1',
+        '-y',
+        output_path
+    ]
+    result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+    if result.returncode != 0:
+        print(f"Failed to extract cover image: {result.stderr}")
+        return False
+    return True
+
+
+def _build_inputs(cmd: List[str], input_file: str, cover_image_path: Optional[str]) -> None:
+    """Add input files to the command."""
+    if cover_image_path:
+        cmd.extend(['-i', cover_image_path])
+    cmd.extend(['-i', input_file])
+
+
+def _build_time_options(cmd: List[str], start_seconds: int, duration_seconds: int) -> None:
+    """Add time-based options to the command."""
+    cmd.extend(['-ss', format_time(start_seconds), '-t', format_time(duration_seconds)])
+
+
+def _build_metadata(cmd: List[str], metadata: Optional[Dict]) -> None:
+    """Add metadata options to the command."""
     cmd.append('-map_metadata')
     cmd.append('-1')
-
-    # Apply custom metadata.
     if metadata:
         for key, value in metadata.items():
             if value is not None and value != '':
                 cmd.extend(['-metadata', f"{key}={value}"])
 
-    # Stream mapping.
+
+def _build_cover_image_mapping(
+    cmd: List[str],
+    audio_codec: Optional[str],
+    video_codec: Optional[str],
+    video_quality: Optional[int],
+) -> None:
+    """Build stream mapping for cover image extraction (audio + cover video)."""
+    cmd.extend(['-map', '1:a:0', '-map', '0:v:0'])
+
+    if video_codec and video_codec != 'copy':
+        cmd.extend(['-c:v', video_codec])
+    else:
+        cmd.extend(['-c:v', 'png'])
+
+    if audio_codec and audio_codec != 'copy':
+        cmd.extend(['-c:a', audio_codec])
+    else:
+        cmd.extend(['-c:a', 'copy'])
+
+    # Preserve attached_pic disposition for cover image
+    cmd.extend(['-disposition', 'attached_pic'])
+
+    cmd.append('-sn')
+
+    if video_quality is not None:
+        cmd.extend(['-q:v', str(video_quality)])
+
+
+def _build_standard_mapping(
+    cmd: List[str],
+    stream_info: Dict,
+    audio_codec: Optional[str],
+    video_codec: Optional[str],
+    subtitle_codec: Optional[str],
+    video_quality: Optional[int],
+    drop_video: bool,
+    drop_subs: bool,
+) -> None:
+    """Build stream mapping for standard extraction (no cover image)."""
     if drop_video and drop_subs:
         cmd.extend(['-map', '0:a:0'])
     elif drop_video:
@@ -228,32 +339,97 @@ def build_ffmpeg_command(input_file: str, start_seconds: int, duration_seconds:
     else:
         cmd.extend(['-map', '0'])
 
-    # Audio codec.
-    if transcode_audio:
-        cmd.extend(['-c:a', transcode_audio])
-        if transcode_audio in ('libmp3lame', 'mp3'):
-            cmd.extend(['-b:a', '192k'])
-        elif transcode_audio in ('libopus', 'opus'):
-            cmd.extend(['-b:a', '128k'])
+    if audio_codec and audio_codec != 'copy':
+        cmd.extend(['-c:a', audio_codec])
     else:
         cmd.extend(['-c:a', 'copy'])
 
-    # Video codec.
-    if not drop_video and stream_info['has_video']:
+    if not drop_video and stream_info.get('has_video'):
+        if video_codec and video_codec != 'copy':
+            cmd.extend(['-c:v', video_codec])
+            if video_quality is not None:
+                cmd.extend(['-q:v', str(video_quality)])
+        else:
             cmd.extend(['-c:v', 'copy'])
     else:
         cmd.append('-vn')
 
-    # Subtitle codec.
-    if not drop_subs and stream_info['has_subtitle']:
+    if not drop_subs and stream_info.get('has_subtitle'):
+        if subtitle_codec and subtitle_codec != 'copy':
+            cmd.extend(['-c:s', subtitle_codec])
+        else:
             cmd.extend(['-c:s', 'copy'])
     else:
         cmd.append('-sn')
 
-    # Output format.
+
+def _build_format(cmd: List[str], format_opt: Optional[str]) -> None:
+    """Add output format option if specified."""
     if format_opt:
-        ffmpeg_format = FORMAT_INFO.get(format_opt, {}).get('ffmpeg', format_opt)
+        ffmpeg_format = next((c['ffmpeg'] for c in CONTAINER_INFO if c['name'] == format_opt), format_opt)
         cmd.extend(['-f', ffmpeg_format])
 
+
+def _build_output(cmd: List[str], output_path: str) -> None:
+    """Add output file to the command."""
     cmd.extend(['-y', output_path])
+
+
+def build_ffmpeg_command(
+    input_file: str,
+    start_seconds: int,
+    duration_seconds: int,
+    output_path: str,
+    stream_info: Dict,
+    format_opt: Optional[str],
+    audio_codec: Optional[str] = 'copy',
+    video_codec: Optional[str] = 'copy',
+    subtitle_codec: Optional[str] = 'copy',
+    metadata: Optional[Dict] = None,
+    cover_image_path: Optional[str] = None,
+    video_quality: Optional[int] = None,
+    drop_video: bool = False,
+    drop_subs: bool = False,
+) -> List[str]:
+    """
+    Construct the FFmpeg command line as a list of arguments.
+
+    Args:
+        input_file: Path to the input media file.
+        start_seconds: Start time for the segment (in seconds).
+        duration_seconds: Duration of the segment (in seconds).
+        output_path: Destination path for the output file.
+        stream_info: Dictionary from get_stream_info().
+        format_opt: Output container format (e.g., 'mp3', 'mkv').
+        audio_codec: Audio codec to use ('copy' or encoder name like 'libopus').
+        video_codec: Video codec to use ('copy' or encoder name).
+        subtitle_codec: Subtitle codec to use ('copy' or encoder name).
+        metadata: Optional dict of metadata key/value pairs to write.
+        cover_image_path: Path to extracted cover image (if any).
+        video_quality: Quality value for video encoder (e.g., 1-31, lower=better).
+        drop_video: If True, remove video streams.
+        drop_subs: If True, remove subtitle streams.
+
+    Returns:
+        A list of command‑line arguments suitable for subprocess.run().
+    """
+    cmd = ['ffmpeg']
+
+    _build_inputs(cmd, input_file, cover_image_path)
+    _build_time_options(cmd, start_seconds, duration_seconds)
+    _build_metadata(cmd, metadata)
+
+    if cover_image_path:
+        _build_cover_image_mapping(cmd, audio_codec, video_codec, video_quality)
+    else:
+        _build_standard_mapping(
+            cmd, stream_info, audio_codec, video_codec, subtitle_codec,
+            video_quality, drop_video, drop_subs
+        )
+
+    _build_format(cmd, format_opt)
+    _build_output(cmd, output_path)
+
     return cmd
+
+

audio_splitter/formats.py

@@ -1,19 +1,28 @@
+# audio_splitter/formats.py
 """Container format decision and validation."""
 
 from typing import Dict, Optional
 
-from .constants import FORMAT_INFO
+from .constants import (
+    CONTAINER_NAMES,
+    CONTAINER_INFO,
+    CODEC_TO_CONTAINER_MAP,
+    COMPATIBILITY_MATRIX,
+    is_audio_codec_supported,
+    is_video_codec_supported,
+)
+from .defaults import DEFAULT_FORMAT
 
 
 def determine_default_format(container: Optional[str], codec: Optional[str]) -> Optional[str]:
     """
     Given the container format and audio codec, determine the recommended output format.
 
-    This is used when the user has not explicitly specified a format.
-    It prioritizes the codec to choose the most appropriate container/extension.
+    Uses the CODEC_TO_CONTAINER_MAP to map codec → container.
+    If the codec is not found, it falls back to the container.
 
     Args:
-        container: Container name (e.g., 'ogg', 'mp4', 'matroska') as returned by get_container_format().
+        container: Container name (e.g., 'ogg', 'mp4', 'mkv') as returned by get_container_format().
         codec: Audio codec name (e.g., 'opus', 'aac', 'mp3') as returned by get_audio_codec().
 
     Returns:
@@ -22,37 +31,13 @@ def determine_default_format(container: Optional[str], codec: Optional[str]) ->
     if not container:
         return None
 
-    # Codec-based decisions (highest priority)
-    if codec == 'opus':
-        return 'opus'
-    if codec in ('aac', 'alac', 'he-aac'):
-        return 'm4a'
-    if codec == 'mp3':
-        return 'mp3'
-    if codec == 'vorbis':
-        return 'ogg'
-    if codec == 'flac':
-        return 'flac'
+    if codec and codec in CODEC_TO_CONTAINER_MAP:
+        fmt = CODEC_TO_CONTAINER_MAP[codec]
+        if fmt in CONTAINER_NAMES:
+            return fmt
 
-    # Container-based fallback (lower priority)
-    if container in ('mp4', 'm4a', 'mov', '3gp'):
-        return 'mp4'
-    if container in ('matroska', 'webm'):
-        return 'matroska'
-    if container in ('ogg',):
-        return 'ogg'
-    if container in ('mp3', 'mpeg'):
-        return 'mp3'
-    if container == 'flac':
-        return 'flac'
-    if container == 'wav':
-        return 'wav'
-    if container == 'aac':
-        return 'aac'
-    if container == 'opus':
-        return 'opus'
-    if container == 'amr':
-        return 'amr'
+    if container in CONTAINER_NAMES:
+        return container
 
     return None
 
@@ -62,69 +47,91 @@ def determine_output_format(stream_info: Dict, user_format: Optional[str],
     """
     Decide which container format to use.
 
-    If user_format is provided, use it.
+    If user_format is provided, map it to the correct container if it's a codec name.
     Else, try to detect the input file's container and codec, and use the recommended format.
     If detection fails or format is not supported, fallback to:
       - MKV if video/subtitles exist
       - MP3 if the audio codec is MP3
       - MP4 (M4A) otherwise
-
-    Args:
-        stream_info: Dict from get_stream_info().
-        user_format: User‑requested format (or None).
-        transcode_audio: Audio codec to transcode to (or None) (unused in this function).
-        input_file: Path to the input file (optional, used to detect container and codec).
-
-    Returns:
-        A format name that exists in FORMAT_INFO.
     """
     if user_format:
+        # Map codec names to their correct containers
+        # e.g., 'opus' -> 'ogg', 'aac' -> 'mp4', etc.
+        if user_format in CODEC_TO_CONTAINER_MAP:
+            return CODEC_TO_CONTAINER_MAP[user_format]
         return user_format
 
-    # If input_file is provided, try to detect container and codec
     if input_file:
         try:
             from .ffmpeg import get_container_format, get_audio_codec
             container = get_container_format(input_file)
-            codec = get_audio_codec(input_file)
-            fmt = determine_default_format(container, codec)
-            if fmt in FORMAT_INFO:
+            audio_codec = get_audio_codec(input_file)
+            fmt = determine_default_format(container, audio_codec)
+            if fmt in CONTAINER_NAMES:
                 return fmt
         except Exception:
-            # If detection fails, fall through to legacy logic
             pass
 
-    # Fallback: legacy behavior
+    # Fallback
     if stream_info.get('has_video') or stream_info.get('has_subtitle'):
-        return 'matroska'
+        return 'mkv'
     audio_codec = stream_info.get('audio_codec', '')
     if audio_codec == 'mp3':
         return 'mp3'
     else:
-        return 'mp4'  # .m4a
+        return 'mp4'
 
 
-def validate_format_compatibility(format_name: str, stream_info: Dict,
-                                  drop_video: bool, drop_subs: bool) -> None:
+def validate_format_compatibility(
+    container: str,
+    stream_info: Dict,
+    drop_video: bool,
+    drop_subs: bool,
+    input_file: Optional[str] = None,
+    audio_codec: Optional[str] = None,
+    video_codec: Optional[str] = None,
+) -> None:
     """
-    Ensure the chosen container can accommodate the streams we intend to keep.
+    Ensure the chosen container and codec combination is valid.
 
     Raises:
-        ValueError: If the format is incompatible with the intended streams.
+        ValueError: If the combination is incompatible.
     """
-    info = FORMAT_INFO.get(format_name)
+    info = next((c for c in CONTAINER_INFO if c['name'] == container), None)
     if not info:
-        print(f"Warning: Unknown format '{format_name}'. Proceeding, but may fail.")
+        print(f"Warning: Unknown container '{container}'. Proceeding, but may fail.")
         return
 
-    if info['audio_only']:
+    # Check if container is audio-only and video is present (unless dropped)
+    if not info['supports_video'] and stream_info.get('has_video') and not drop_video:
+        raise ValueError(
+            f"Container '{container}' does not support video streams. "
+            "Please use --drop-video or choose a container that supports video (e.g., MKV, MP4)."
+        )
+
+    # Determine actual audio codec for validation
+    # When 'copy' is used, we must still validate the input codec against the container
+    actual_audio_codec = audio_codec if audio_codec and audio_codec != 'copy' else stream_info.get('audio_codec')
+    if actual_audio_codec:
+        if not is_audio_codec_supported(container, actual_audio_codec):
+            raise ValueError(
+                f"Container '{container}' does not support audio codec '{actual_audio_codec}'. "
+                f"Please choose a different container or audio codec."
+            )
+
+    # Check if video codec is supported (if video is present and not dropped)
     if stream_info.get('has_video') and not drop_video:
+        # Determine the video codec from input file if not provided
+        if video_codec is None and input_file:
+            from .ffmpeg import get_video_codec
+            video_codec = get_video_codec(input_file)
+        # When 'copy' is used, validate the input video codec against the container
+        if video_codec == 'copy' and input_file:
+            from .ffmpeg import get_video_codec
+            video_codec = get_video_codec(input_file)
+        if video_codec:
+            if not is_video_codec_supported(container, video_codec):
                 raise ValueError(
-                f"Format '{format_name}' does not support video streams. "
-                "Please use --drop-video or choose a container that supports video."
-            )
-        if stream_info.get('has_subtitle') and not drop_subs:
-            raise ValueError(
-                f"Format '{format_name}' does not support subtitle streams. "
-                "Please use --drop-subs or choose a container that supports subtitles."
+                    f"Container '{container}' does not support video codec '{video_codec}'. "
+                    f"Please choose a different container, drop video, or transcode video to a supported codec."
                 )

audio_splitter/handlers.py

@@ -0,0 +1,167 @@
+# audio_splitter/handlers.py
+"""Handler system for cover image attachment.
+
+This module provides a registry of handlers for different
+codec + image combinations. Each handler is responsible for
+attaching the cover image to the output file in the appropriate way.
+"""
+
+import os
+import subprocess
+from typing import Dict, Optional
+
+
+def _run_opustags(input_file: str, cover_image_path: str, output_path: Optional[str] = None) -> bool:
+    """
+    Run opustags to attach a cover image to an Opus file.
+
+    Args:
+        input_file: Path to the input Opus file.
+        cover_image_path: Path to the cover image.
+        output_path: Optional output path (if None, overwrites input).
+
+    Returns:
+        True if successful, False otherwise.
+    """
+    cmd = ['opustags', '--set-cover', cover_image_path, input_file]
+
+    if output_path:
+        cmd.extend(['-o', output_path, '-y'])
+    else:
+        cmd.extend(['-i'])
+
+    result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+    if result.returncode != 0:
+        print(f"opustags failed: {result.stderr}")
+        return False
+    return True
+
+
+def _handler_default(
+    input_file: str,
+    cover_image_path: str,
+    output_path: str,
+    stream_info: Dict,
+    audio_codec: str,
+    video_codec: str,
+    video_quality: Optional[int],
+    drop_video: bool,
+    drop_subs: bool,
+) -> bool:
+    """
+    Default handler: use ffmpeg with -disposition attached_pic.
+
+    This is the standard approach for formats like MP3, FLAC, etc.
+    """
+    # This handler doesn't do anything - the cover is already handled
+    # by the ffmpeg command in core.py via build_ffmpeg_command()
+    # We just return True to indicate success.
+    return True
+
+
+def _handler_opus_with_cover(
+    input_file: str,
+    cover_image_path: str,
+    output_path: str,
+    stream_info: Dict,
+    audio_codec: str,
+    video_codec: str,
+    video_quality: Optional[int],
+    drop_video: bool,
+    drop_subs: bool,
+) -> bool:
+    """
+    Handler for Opus files with cover image.
+
+    Uses opustags to attach the cover image after the file is processed.
+    """
+    return _run_opustags(output_path, cover_image_path)
+
+
+def _handler_mp3_with_cover(
+    input_file: str,
+    cover_image_path: str,
+    output_path: str,
+    stream_info: Dict,
+    audio_codec: str,
+    video_codec: str,
+    video_quality: Optional[int],
+    drop_video: bool,
+    drop_subs: bool,
+) -> bool:
+    """
+    Handler for MP3 files with cover image.
+
+    Uses ffmpeg with -disposition attached_pic.
+    """
+    # MP3 handler - the cover is already attached by ffmpeg in core.py
+    return True
+
+
+def _handler_flac_with_cover(
+    input_file: str,
+    cover_image_path: str,
+    output_path: str,
+    stream_info: Dict,
+    audio_codec: str,
+    video_codec: str,
+    video_quality: Optional[int],
+    drop_video: bool,
+    drop_subs: bool,
+) -> bool:
+    """
+    Handler for FLAC files with cover image.
+
+    Uses ffmpeg with -disposition attached_pic.
+    """
+    # FLAC handler - the cover is already attached by ffmpeg in core.py
+    return True
+
+
+# Handler registry: maps (output_container, input_codec) to handler function
+HANDLER_REGISTRY: Dict[tuple, callable] = {
+    ('opus', 'opus'): _handler_opus_with_cover,
+    ('ogg', 'opus'): _handler_opus_with_cover,
+    ('mp3', 'mp3'): _handler_mp3_with_cover,
+    ('flac', 'flac'): _handler_flac_with_cover,
+}
+
+
+def get_handler(output_container: str, input_audio_codec: Optional[str] = None):
+    """
+    Get the appropriate handler for the given container and input codec.
+
+    Args:
+        output_container: Output container format (e.g., 'opus', 'mp3', 'flac').
+        input_audio_codec: Input audio codec (e.g., 'opus', 'mp3', 'flac').
+
+    Returns:
+        Handler function, or the default handler if no specific handler is found.
+    """
+    if input_audio_codec:
+        key = (output_container, input_audio_codec)
+        if key in HANDLER_REGISTRY:
+            return HANDLER_REGISTRY[key]
+
+    # Fall back to container-only key
+    if (output_container, None) in HANDLER_REGISTRY:
+        return HANDLER_REGISTRY[(output_container, None)]
+
+    # Default handler
+    return _handler_default
+
+
+def needs_drop_video(output_container: str, input_audio_codec: Optional[str] = None) -> bool:
+    """
+    Check if the handler requires dropping video even if user didn't specify --drop-video.
+
+    Args:
+        output_container: Output container format.
+        input_audio_codec: Input audio codec.
+
+    Returns:
+        True if video should be dropped, False otherwise.
+    """
+    handler = get_handler(output_container, input_audio_codec)
+    # The opus handler requires dropping video
+    return handler == _handler_opus_with_cover

audio_splitter/main.py

@@ -1,139 +1,182 @@
-"""Command‑line interface and entry point."""
+#!/usr/bin/env python3
+"""
+Audio Splitter – Command‑Line Interface
+
+Split an audio file into tracks using a tracklist file.
+
+Usage:
+    audio_splitter input.mp3 tracklist.txt [OPTIONS]
+"""
 
 import os
 import sys
 import subprocess
 import argparse
 
-from .constants import DEFAULT_BAD_CHARS
-from .tracklist import read_tracklist, parse_format
+from .defaults import (
+    DEFAULT_FORMAT,
+    DEFAULT_OUTPUT_TEMPLATE,
+    DEFAULT_REPLACEMENT_CHAR,
+    DEFAULT_BAD_CHARS,
+    DEFAULT_TRACKLIST_FORMAT,
+    DEFAULT_ALBUM,
+    DEFAULT_COMMENT,
+    DEFAULT_COMMENT_STREAM,
+    DEFAULT_COMMENT_SEPARATOR,
+    DEFAULT_NO_COMMENT,
+    DEFAULT_MERGE_COMMENTS,
+    DEFAULT_DROP_VIDEO,
+    DEFAULT_DROP_SUBS,
+    DEFAULT_NUMBER_TRACKS,
+    DEFAULT_REPLACE_BAD_CHARS,
+    DEFAULT_SKIP_EXISTING,
+    DEFAULT_DELETE_ORIGINAL,
+)
 from .core import split_audio
+from .tracklist import read_tracklist, parse_format
 
 
 def main():
-    """Parse arguments and start the splitting process."""
     parser = argparse.ArgumentParser(
         description="Split an audio file into tracks using a tracklist.",
-        epilog="Tracklist format: mm:ss track_name - author_name"
+        epilog="Tracklist format: mm:ss track_name - author_name (or custom with --tracklist-format)"
     )
 
-    # Positional arguments.
-    parser.add_argument('input_file', help='Input audio/video file')
+    # Positional
+    parser.add_argument('input_file', help='Input audio file')
     parser.add_argument('tracklist_file', help='Tracklist file')
 
-    # Optional arguments.
+    # Container and codec options
     parser.add_argument(
-        '--output-dir', '-o',
-        help='Output directory for split tracks (default: <input_basename>_splits)'
+        '--container',
+        default=None,
+        help="Output container format (auto-detect if not specified)"
     )
     parser.add_argument(
-        '--format',
-        help='Output container format (e.g., mp3, m4a, mkv, mp4, ogg, opus)'
+        '--audio-codec',
+        default='copy',
+        help="Audio codec (copy or encoder name, e.g., libopus)"
     )
     parser.add_argument(
-        '--transcode-to',
-        help='Re-encode audio to this codec (e.g., libmp3lame, aac, libopus)'
+        '--video-codec',
+        default='copy',
+        help="Video codec (copy or encoder name, e.g., libx264)"
+    )
+    parser.add_argument(
+        '--subtitle-codec',
+        default='copy',
+        help="Subtitle codec (copy or encoder name, e.g., srt)"
+    )
+    parser.add_argument(
+        '--video-quality', '-vq',
+        type=int,
+        default=None,
+        help="Video quality (integer, encoder-specific; usually 1-31, lower=better). "
+             "If omitted, FFmpeg default is used."
     )
     parser.add_argument(
         '--drop-video',
         action='store_true',
-        help='Remove video streams from output'
+        default=DEFAULT_DROP_VIDEO,
+        help="Drop video streams"
     )
     parser.add_argument(
         '--drop-subs',
         action='store_true',
-        help='Remove subtitle streams from output'
+        default=DEFAULT_DROP_SUBS,
+        help="Drop subtitle streams"
     )
+
+    # Filename options
     parser.add_argument(
         '--number-tracks',
         action='store_true',
-        help='Prepend track number to output filenames (convenience; use %%num in template for full control)'
+        default=DEFAULT_NUMBER_TRACKS,
+        help="Prepend track numbers"
+    )
+    parser.add_argument(
+        '--output-template',
+        default=DEFAULT_OUTPUT_TEMPLATE,
+        help="Output filename template (default: %(default)s)"
     )
     parser.add_argument(
         '--replace-bad-chars',
         action='store_true',
-        help='Replace problematic characters in filenames (default: off)'
+        default=DEFAULT_REPLACE_BAD_CHARS,
+        help="Replace bad characters"
     )
     parser.add_argument(
         '--replacement-char',
-        default='_',
-        help='Character used as replacement (default: "_")'
+        default=DEFAULT_REPLACEMENT_CHAR,
+        help="Replacement character (default: %(default)s)"
     )
     parser.add_argument(
         '--bad-chars',
         default=DEFAULT_BAD_CHARS,
-        help='String of characters to replace (default includes space and single quote)'
+        help="Bad characters to replace (default: %(default)s)"
     )
     parser.add_argument(
         '--skip-existing',
         action='store_true',
-        help='Skip extraction if output file already exists (default: overwrite)'
-    )
-    parser.add_argument(
-        '--tracklist-format',
-        default='%ts %tn - %an',
-        help='Format of each line in the tracklist using placeholders: '
-             '%%ts (timestamp), %%tn (track name), %%an (author), %%al (album), '
-             '%%date (date/year), %%ext (file extension). '
-             'Default: "%%ts %%tn - %%an"'
-    )
-    parser.add_argument(
-        '--output-template',
-        default='%an-%tn.%ext',
-        help='Template for output filenames using placeholders: '
-             '%%tn (track name), %%an (author), %%al (album), '
-             '%%date (date/year), %%ext (file extension), %%num (track number). '
-             'Default: "%%an-%%tn.%%ext"'
-    )
-    parser.add_argument(
-        '--dry-run',
-        action='store_true',
-        help='Parse and display the tracklist without splitting any files'
+        default=DEFAULT_SKIP_EXISTING,
+        help="Skip existing output files"
     )
 
-    # Metadata options.
-    parser.add_argument(
-        '--album',
-        help='Set album name in output metadata (overrides parsed %%al and original album)'
-    )
-    parser.add_argument(
-        '--comment',
-        help='Explicit comment text (overrides all other comment settings)'
-    )
+    # Metadata
+    parser.add_argument('--album', default=DEFAULT_ALBUM, help="Album name")
+    parser.add_argument('--comment', default=DEFAULT_COMMENT, help="Comment")
     parser.add_argument(
         '--no-comment',
         action='store_true',
-        help='Explicitly ignore any comment (no comment written)'
+        default=DEFAULT_NO_COMMENT,
+        help="Ignore comment"
     )
     parser.add_argument(
         '--comment-stream',
         type=int,
-        default=None,
-        help='Select comment from a specific stream index (0‑based). Default: first stream with a comment.'
+        default=DEFAULT_COMMENT_STREAM,
+        help="Comment stream index"
     )
     parser.add_argument(
         '--merge-comments',
         action='store_true',
-        help='Merge all comments from all streams into one (separated by --comment-separator)'
+        default=DEFAULT_MERGE_COMMENTS,
+        help="Merge all comments"
     )
     parser.add_argument(
         '--comment-separator',
-        default='; ',
-        help='Separator used when merging comments (default: "; ")'
+        default=DEFAULT_COMMENT_SEPARATOR,
+        help="Separator for merged comments (default: %(default)s)"
     )
 
-    # NEW: Delete original after successful split.
+    # Tracklist format
+    parser.add_argument(
+        '--tracklist-format',
+        default=DEFAULT_TRACKLIST_FORMAT,
+        help="Tracklist format (default: %(default)s)"
+    )
+
+    # Other
     parser.add_argument(
         '--delete-original',
         action='store_true',
-        help='Delete the original input file after successful splitting (default: keep)'
+        default=DEFAULT_DELETE_ORIGINAL,
+        help="Delete original file after split"
+    )
+    parser.add_argument(
+        '--dry-run',
+        action='store_true',
+        help="Parse and display tracklist without splitting"
+    )
+    parser.add_argument(
+        '--output-dir', '-o',
+        default=None,
+        help="Output directory (default: <input_basename>_splits)"
     )
 
     args = parser.parse_args()
 
-    # --------------------------------------------------------------------------
-    # Input validation
-    # --------------------------------------------------------------------------
+    # Validate input
     if not os.path.exists(args.input_file):
         print(f"Error: Input file not found: {args.input_file}")
         sys.exit(1)
@@ -142,12 +185,7 @@ def main():
         print(f"Error: Tracklist file not found: {args.tracklist_file}")
         sys.exit(1)
 
-    # Ensure the replacement character is a single character.
-    if len(args.replacement_char) != 1:
-        print("Error: --replacement-char must be a single character.")
-        sys.exit(1)
-
-    # Check that FFmpeg is installed.
+    # Check FFmpeg
     try:
         subprocess.run(['ffmpeg', '-version'], capture_output=True, check=True)
     except (subprocess.CalledProcessError, FileNotFoundError):
@@ -155,14 +193,14 @@ def main():
         print("  - https://ffmpeg.org/download.html")
         sys.exit(1)
 
-    # Parse the tracklist using the user‑provided format.
+    # Parse tracklist format
     try:
         tokens = parse_format(args.tracklist_format)
-    except ValueError as error:
-        print(f"Error in --tracklist-format: {error}")
+    except ValueError as e:
+        print(f"Error in --tracklist-format: {e}")
         sys.exit(1)
 
-    # Read and parse the tracklist file.
+    # Read tracklist
     tracks = read_tracklist(args.tracklist_file, tokens)
     if not tracks:
         print("Error: No valid tracks found in tracklist file.")
@@ -170,7 +208,6 @@ def main():
 
     print(f"Found {len(tracks)} tracks.")
 
-    # Dry‑run mode: display parsed data and exit.
     if args.dry_run:
         print("\nParsed tracklist:")
         print("-" * 60)
@@ -184,34 +221,22 @@ def main():
                 print(f"{idx:3d} | " + " | ".join(values))
         print("-" * 60)
         print("Dry‑run complete. No files were created.")
-        sys.exit(0)
+        return
 
-    # Determine the output directory.
+    # Determine output directory
     if args.output_dir:
         output_dir = args.output_dir
-        print(f"Using custom output directory: {output_dir}")
     else:
         base_name = os.path.splitext(os.path.basename(args.input_file))[0]
         output_dir = base_name + "_splits"
-        print(f"Using default output directory: {output_dir}")
 
-    # Run the splitter.
+    # Run split
     try:
         split_audio(args.input_file, output_dir, tracks, args)
-    except (RuntimeError, ValueError) as error:
-        print(f"Error: {error}")
+    except Exception as e:
+        print(f"Error during split: {e}")
         sys.exit(1)
 
-    # --------------------------------------------------------------------------
-    # Delete original file if requested and successful.
-    # --------------------------------------------------------------------------
-    if args.delete_original:
-        try:
-            os.remove(args.input_file)
-            print(f"Deleted original file: {args.input_file}")
-        except OSError as e:
-            print(f"Warning: Could not delete original file: {e}")
-
     print("Done!")
 
 

docker-compose.override.yaml

@@ -1,37 +0,0 @@
-services:
-  backend:
-    build:
-      context: .
-      dockerfile: web/backend/Dockerfile
-    volumes:
-      # Bind mount for source code (hot-reload for Python)
-      - ./web/backend:/app/backend
-      - ./audio_splitter:/app/audio_splitter
-      - ./setup.py:/app/setup.py
-      - ./pyproject.toml:/app/pyproject.toml
-      # Development data directory (overrides production)
-      - "./dev_data:/tmp/audio_splitter_web"
-    environment:
-      - DEBUG=1
-      - PYTHONUNBUFFERED=1
-    ports:
-      - "8000:8000"
-
-  frontend:
-    build:
-      context: ./web/frontend
-       # Use the same Dockerfile, but override CMD for development
-      dockerfile: Dockerfile
-    command: ["npm", "run", "dev", "--", "--host", "0.0.0.0"]
-    volumes:
-      # Bind mount for source code (hot-reload for Vite)
-      - ./web/frontend:/app
-      - node_modules:/app/node_modules
-    environment:
-      - BACKEND_URL=http://backend:8000
-      - VITE_BACKEND_URL=http://backend:8000
-    ports:
-      - "5173:5173"
-
-volumes:
-  node_modules:

docker-compose.yaml

@@ -1,19 +1,24 @@
 services:
   backend:
-    image: git.vmn.su/max/audio_splitter_backend:latest
+    build:
+      context: .
+      dockerfile: web/backend/Dockerfile
+      #image: max/audio_splitter_backend:latest
     ports:
       - "${BACKEND_PORT:-8000}:8000"
     volumes:
-      # Bind mount for persistent data storage.
-      # Set BACKEND_DATA_DIR in .env to point to your data directory.
-      - "${BACKEND_DATA_DIR:-/var/lib/audio_splitter_data}:/tmp/audio_splitter_web"
+      #- "${BACKEND_DATA_DIR:-/var/lib/audio_splitter_data}:/tmp/audio_splitter_web"
+      - "/tmp/test:/tmp/audio_splitter_web"
     environment:
       - PYTHONUNBUFFERED=1
       - DEBUG=${DEBUG:-0}
     restart: unless-stopped
 
   frontend:
-    image: git.vmn.su/max/audio_splitter_frontend:latest
+    build:
+      context: .
+      dockerfile: web/frontend/Dockerfile
+    #image: max/audio_splitter_frontend:latest
     ports:
       - "${FRONTEND_PORT:-5173}:80"
     depends_on:

docker-entrypoint.sh

@@ -1,18 +0,0 @@
-#!/bin/bash
-set -e
-
-# Check if we are running as root (default)
-if [ "$(id -u)" = "0" ]; then
-    # If /data is a directory, change its ownership to the container user
-    if [ -d "/data" ]; then
-        echo "Setting ownership of /data to appuser:appgroup"
-        chown -R appuser:appgroup /data
-    fi
-
-    # Drop privileges and run audio_splitter with the provided arguments
-    exec gosu appuser audio_splitter "$@"
-else
-    # If not root, just run audio_splitter directly
-    # It's not supposed to be called
-    exec audio_splitter "$@"
-fi

scripts/generate_ts_defaults.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+"""
+Generate TypeScript constants from audio_splitter/defaults.py.
+"""
+
+import importlib.util
+import json
+import sys
+from pathlib import Path
+
+# Get the directory where this script is located
+SCRIPT_DIR = Path(__file__).parent.absolute()
+
+# The defaults.py is in the same directory as the script
+DEFAULTS_PATH = SCRIPT_DIR / "defaults.py"
+
+# The frontend source is at SCRIPT_DIR.parent (i.e., /app)
+# The generated file should be at /app/src/constants/generated.ts
+FRONTEND_ROOT = SCRIPT_DIR.parent
+OUTPUT_PATH = FRONTEND_ROOT / "src" / "constants" / "generated.ts"
+
+
+def load_defaults_module():
+    spec = importlib.util.spec_from_file_location("defaults", DEFAULTS_PATH)
+    if spec is None:
+        raise RuntimeError(f"Could not load spec for {DEFAULTS_PATH}")
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module
+
+
+def format_value(value):
+    """Convert Python value to TypeScript literal."""
+    if value is None:
+        return "null"
+    if isinstance(value, bool):
+        return str(value).lower()
+    if isinstance(value, str):
+        # Use json.dumps to produce a properly escaped string literal
+        return json.dumps(value)
+    if isinstance(value, (int, float)):
+        return str(value)
+    if isinstance(value, list):
+        return f"[{', '.join(format_value(v) for v in value)}]"
+    return repr(value)
+
+
+def main():
+    print(f"Generating TypeScript defaults from {DEFAULTS_PATH}")
+    defaults = load_defaults_module()
+
+    constants = {name: value for name, value in vars(defaults).items() if name.startswith("DEFAULT_")}
+
+    if not constants:
+        print("No DEFAULT_* constants found.")
+        sys.exit(1)
+
+    lines = [
+        "// ============================================================================",
+        "// GENERATED FILE – DO NOT EDIT MANUALLY.",
+        "// This file is generated from audio_splitter/defaults.py.",
+        "// Run `npm run generate` or `python scripts/generate_ts_defaults.py` to update.",
+        "// ============================================================================",
+        "",
+    ]
+
+    for name, value in sorted(constants.items()):
+        ts_value = format_value(value)
+        lines.append(f"export const {name} = {ts_value};")
+
+    OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)
+    OUTPUT_PATH.write_text("\n".join(lines) + "\n")
+
+    print(f"✅ Generated {OUTPUT_PATH}")
+    print(f"   {len(constants)} constants exported.")
+
+
+if __name__ == "__main__":
+    main()

web/backend/Dockerfile

@@ -1,9 +1,10 @@
 FROM python:3.13-slim
 
-# Install FFmpeg, system dependencies, and gosu from APT
+# Install FFmpeg, opustags, system dependencies, and gosu from APT
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
         ffmpeg \
+        opustags \
         ca-certificates \
         gosu \
         && \

web/backend/api/__init__.py

@@ -1,4 +1,3 @@
 """API route handlers."""
 
-from . import upload, split, status, download
-# websocket is imported directly in main.py to avoid circular import
+from . import upload, split, split_file, status, download, websocket, formats, info

web/backend/api/formats.py

@@ -1,8 +1,9 @@
+# web/backend/api/formats.py
 """Endpoint to expose format information to the frontend."""
 
 from fastapi import APIRouter
 
-from backend.constants import FORMAT_INFO
+from audio_splitter.constants import CONTAINER_INFO, CODEC_INFO
 
 router = APIRouter(prefix="/api", tags=["formats"])
 
@@ -10,16 +11,9 @@ router = APIRouter(prefix="/api", tags=["formats"])
 @router.get("/formats")
 async def get_formats():
     """
-    Return the list of supported container formats with their properties.
+    Return the list of supported containers and codecs.
     """
     return {
-        "formats": [
-            {
-                "name": name,
-                "ffmpeg": info["ffmpeg"],
-                "extension": info["ext"],
-                "audio_only": info["audio_only"],
-            }
-            for name, info in FORMAT_INFO.items()
-        ]
+        "containers": CONTAINER_INFO,
+        "codecs": CODEC_INFO,
     }

web/backend/api/info.py

@@ -5,7 +5,12 @@ from fastapi import APIRouter, HTTPException
 from backend.config import settings
 from backend.services.file_manager import FileManager
 from backend.services.task_manager import task_manager
-from backend.ffmpeg import get_stream_info
+
+# Import core functions
+from audio_splitter.ffmpeg import get_stream_info, get_container_format, get_audio_codec
+from audio_splitter.formats import determine_default_format
+from audio_splitter.constants import CONTAINER_NAMES
+from audio_splitter.defaults import DEFAULT_FORMAT
 
 router = APIRouter(prefix="/api", tags=["info"])
 
@@ -13,7 +18,8 @@ router = APIRouter(prefix="/api", tags=["info"])
 @router.get("/info/{task_id}")
 async def get_task_info(task_id: str):
     """
-    Return stream information (has_audio, has_video, has_subtitle) for the uploaded file.
+    Return stream information (has_audio, has_video, has_subtitle, audio_codec)
+    for the uploaded file.
     """
     if not task_manager.has_task(task_id):
         raise HTTPException(status_code=404, detail=f"Task {task_id} not found")
@@ -33,3 +39,34 @@ async def get_task_info(task_id: str):
         }
     except Exception as e:
         raise HTTPException(status_code=500, detail=f"Failed to retrieve stream info: {str(e)}")
+
+
+@router.get("/info/recommended-format/{task_id}")
+async def get_recommended_format(task_id: str):
+    """
+    Return the recommended output format (container name) for the uploaded file,
+    based on its container and audio codec.
+    """
+    if not task_manager.has_task(task_id):
+        raise HTTPException(status_code=404, detail=f"Task {task_id} not found")
+
+    input_path = FileManager.get_input_path(task_id)
+    if not input_path or not input_path.exists():
+        raise HTTPException(status_code=404, detail="Input file not found")
+
+    try:
+        container = get_container_format(str(input_path))
+        codec = get_audio_codec(str(input_path))
+
+        fmt = determine_default_format(container, codec)
+
+        # Fallback if detection fails or format is unsupported
+        if fmt is None:
+            fmt = DEFAULT_FORMAT
+        if fmt not in CONTAINER_NAMES:
+            fmt = "mp3"  # ultimate fallback
+
+        return {"format": fmt}
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Failed to determine format: {str(e)}")

web/backend/api/split.py

@@ -1,4 +1,4 @@
-"""Split task endpoint."""
+"""Split task endpoint (JSON tracklist)."""
 
 from fastapi import APIRouter, HTTPException, BackgroundTasks
 
@@ -24,6 +24,29 @@ async def start_split(request: SplitRequest, background_tasks: BackgroundTasks):
             detail=f"Task {task_id} is already {status['status']}"
         )
 
+    # Build options dict from request
+    options = {
+        "container": request.container,
+        "audio_codec": request.audio_codec,
+        "video_codec": request.video_codec,
+        "subtitle_codec": request.subtitle_codec,
+        "video_quality": request.video_quality,
+        "drop_video": request.drop_video,
+        "drop_subs": request.drop_subs,
+        "number_tracks": request.number_tracks,
+        "replace_bad_chars": request.replace_bad_chars,
+        "replacement_char": request.replacement_char,
+        "bad_chars": request.bad_chars,
+        "skip_existing": request.skip_existing,
+        "output_template": request.output_template,
+        "album": request.album,
+        "comment": request.comment,
+        "no_comment": request.no_comment,
+        "comment_stream": request.comment_stream,
+        "merge_comments": request.merge_comments,
+        "comment_separator": request.comment_separator,
+    }
+
     task_manager.update_task(
         task_id,
         status=TaskStatus.PROCESSING,
@@ -31,7 +54,12 @@ async def start_split(request: SplitRequest, background_tasks: BackgroundTasks):
         message="Preparing to split..."
     )
 
-    background_tasks.add_task(run_split_task, task_id, request.tracklist, request.options)
+    background_tasks.add_task(
+        run_split_task,
+        task_id,
+        request.tracklist,
+        options
+    )
 
     return SplitResponse(
         task_id=task_id,

web/backend/api/split_file.py

@@ -0,0 +1,151 @@
+"""Endpoint for splitting with a tracklist file upload."""
+
+import json
+from pathlib import Path
+from typing import Optional
+
+from fastapi import APIRouter, UploadFile, File, Form, HTTPException, BackgroundTasks
+
+from backend.config import settings
+from backend.services.task_manager import task_manager
+from backend.services.splitter import run_split_task
+from backend.models.request import TracklistEntry
+from backend.models.response import SplitResponse, TaskStatus
+
+router = APIRouter(prefix="/api", tags=["split"])
+
+from audio_splitter.tracklist import parse_format, read_tracklist
+
+
+@router.post("/split-file", response_model=SplitResponse)
+async def split_from_file(
+    background_tasks: BackgroundTasks,
+    task_id: str = Form(...),
+    tracklist_file: UploadFile = File(...),
+    # New fields
+    container: Optional[str] = Form(None),
+    audio_codec: str = Form("copy"),
+    video_codec: str = Form("copy"),
+    subtitle_codec: str = Form("copy"),
+    video_quality: Optional[int] = Form(None),
+    drop_video: bool = Form(False),
+    drop_subs: bool = Form(False),
+    number_tracks: bool = Form(False),
+    replace_bad_chars: bool = Form(False),
+    replacement_char: str = Form("_"),
+    bad_chars: str = Form(r'!@#№$;:%^&?*(){}[]\/<>+=~`\' '),
+    skip_existing: bool = Form(False),
+    output_template: str = Form("%an-%tn.%ext"),
+    album: Optional[str] = Form(None),
+    comment: Optional[str] = Form(None),
+    no_comment: bool = Form(False),
+    comment_stream: Optional[int] = Form(None),
+    merge_comments: bool = Form(False),
+    comment_separator: str = Form("; "),
+    options: str = Form("{}"),  # backward-compatible, but we now use explicit fields
+    tracklist_format: str = Form("%ts %tn - %an"),
+):
+    # Validate task exists
+    if not task_manager.has_task(task_id):
+        raise HTTPException(status_code=404, detail=f"Task {task_id} not found")
+
+    status = task_manager.get_status(task_id)
+    if status and status["status"] in (TaskStatus.PROCESSING, TaskStatus.DONE):
+        raise HTTPException(
+            status_code=409,
+            detail=f"Task {task_id} is already {status['status']}"
+        )
+
+    if not tracklist_file.filename.endswith(('.txt', '.text')):
+        raise HTTPException(
+            status_code=400,
+            detail="Tracklist file must be a text file (.txt or .text)"
+        )
+
+    try:
+        content = await tracklist_file.read()
+        text = content.decode('utf-8')
+    except UnicodeDecodeError:
+        raise HTTPException(
+            status_code=400,
+            detail="Tracklist file must be UTF-8 encoded"
+        )
+
+    if not text.strip():
+        raise HTTPException(
+            status_code=400,
+            detail="Tracklist file is empty"
+        )
+
+    # Parse tracklist using CLI logic
+    try:
+        tokens = parse_format(tracklist_format)
+        temp_tracklist_path = settings.temp_dir / task_id / "tracklist.txt"
+        temp_tracklist_path.parent.mkdir(parents=True, exist_ok=True)
+        temp_tracklist_path.write_text(text, encoding='utf-8')
+
+        tracklist_dicts = read_tracklist(str(temp_tracklist_path), tokens)
+
+    except Exception as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Failed to parse tracklist: {str(e)}"
+        )
+
+    if not tracklist_dicts:
+        raise HTTPException(
+            status_code=400,
+            detail="No valid tracks found in tracklist file"
+        )
+
+    # Convert dicts to TracklistEntry objects
+    try:
+        tracklist_entries = [TracklistEntry(**entry) for entry in tracklist_dicts]
+    except Exception as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Invalid tracklist data: {str(e)}"
+        )
+
+    # Build options dict from explicit fields (ignore `options` parameter)
+    options = {
+        "container": container,
+        "audio_codec": audio_codec,
+        "video_codec": video_codec,
+        "subtitle_codec": subtitle_codec,
+        "video_quality": video_quality,
+        "drop_video": drop_video,
+        "drop_subs": drop_subs,
+        "number_tracks": number_tracks,
+        "replace_bad_chars": replace_bad_chars,
+        "replacement_char": replacement_char,
+        "bad_chars": bad_chars,
+        "skip_existing": skip_existing,
+        "output_template": output_template,
+        "album": album,
+        "comment": comment,
+        "no_comment": no_comment,
+        "comment_stream": comment_stream,
+        "merge_comments": merge_comments,
+        "comment_separator": comment_separator,
+    }
+
+    # Update task status
+    task_manager.update_task(
+        task_id,
+        status=TaskStatus.PROCESSING,
+        progress=0,
+        message="Preparing to split..."
+    )
+
+    background_tasks.add_task(
+        run_split_task,
+        task_id,
+        tracklist_entries,
+        options
+    )
+
+    return SplitResponse(
+        task_id=task_id,
+        status=TaskStatus.PROCESSING
+    )

web/backend/constants.py

@@ -1,12 +0,0 @@
-FORMAT_INFO = {
-    'mp3':      {'ffmpeg': 'mp3',      'ext': '.mp3',  'audio_only': True},
-    'm4a':      {'ffmpeg': 'mp4',      'ext': '.m4a',  'audio_only': True},
-    'mp4':      {'ffmpeg': 'mp4',      'ext': '.mp4',  'audio_only': False},
-    'mkv':      {'ffmpeg': 'matroska', 'ext': '.mkv',  'audio_only': False},
-    'matroska': {'ffmpeg': 'matroska', 'ext': '.mkv',  'audio_only': False},
-    'ogg':      {'ffmpeg': 'ogg',      'ext': '.ogg',  'audio_only': True},
-    'opus':     {'ffmpeg': 'ogg',      'ext': '.opus', 'audio_only': True},
-    'flac':     {'ffmpeg': 'flac',     'ext': '.flac', 'audio_only': True},
-    'wav':      {'ffmpeg': 'wav',      'ext': '.wav',  'audio_only': True},
-    'aac':      {'ffmpeg': 'adts',     'ext': '.aac',  'audio_only': True},
-}

web/backend/main.py

@@ -5,7 +5,7 @@ from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 
 from backend.config import settings
-from backend.api import upload, split, status, download, websocket, formats, info
+from backend.api import upload, split, split_file, status, download, websocket, formats, info
 from backend.services import progress_publisher
 
 app = FastAPI(
@@ -33,11 +33,12 @@ async def startup_event():
 # Include routers
 app.include_router(upload.router)
 app.include_router(split.router)
+app.include_router(split_file.router)  # NEW
 app.include_router(status.router)
 app.include_router(download.router)
 app.include_router(websocket.router)
-app.include_router(formats.router)   # new
-app.include_router(info.router)      # new
+app.include_router(formats.router)
+app.include_router(info.router)
 
 
 @app.get("/")

web/backend/models/request.py

@@ -17,19 +17,16 @@ class TracklistEntry(BaseModel):
 
     @validator("ts")
     def validate_timestamp(cls, v: str) -> str:
-        """Basic timestamp validation (format and range)."""
         v = v.strip()
         if not v:
             raise ValueError("Timestamp cannot be empty")
 
-        # Check for range format (start-end)
         if "-" in v:
             parts = v.split("-", 1)
             start = parts[0].strip()
             end = parts[1].strip()
             if not start or not end:
                 raise ValueError("Invalid range format. Expected 'start-end'")
-            # Validate each part with the same logic
             for ts in [start, end]:
                 cls._validate_single_timestamp(ts)
         else:
@@ -39,7 +36,6 @@ class TracklistEntry(BaseModel):
 
     @staticmethod
     def _validate_single_timestamp(ts: str) -> None:
-        """Validate a single timestamp (mm:ss or HH:MM:SS)."""
         parts = ts.split(":")
         if len(parts) not in (2, 3):
             raise ValueError(f"Invalid timestamp format: {ts}. Expected mm:ss or HH:MM:SS")
@@ -55,4 +51,30 @@ class SplitRequest(BaseModel):
 
     task_id: str = Field(..., description="Task ID from upload")
     tracklist: List[TracklistEntry] = Field(..., description="List of tracks")
-    options: dict = Field(default_factory=dict, description="All CLI options")
+
+    # Container and codec options
+    container: Optional[str] = Field(None, description="Output container (auto-detect if None)")
+    audio_codec: Optional[str] = Field("copy", description="Audio codec (copy or encoder name)")
+    video_codec: Optional[str] = Field("copy", description="Video codec (copy or encoder name)")
+    subtitle_codec: Optional[str] = Field("copy", description="Subtitle codec (copy or encoder name)")
+    video_quality: Optional[int] = Field(None, description="Video quality (encoder-specific integer)")
+
+    # Stream handling
+    drop_video: bool = Field(False, description="Remove video streams")
+    drop_subs: bool = Field(False, description="Remove subtitle streams")
+
+    # Filename options
+    number_tracks: bool = Field(False, description="Prepend track numbers")
+    replace_bad_chars: bool = Field(False, description="Replace bad characters")
+    replacement_char: str = Field("_", description="Replacement character")
+    bad_chars: str = Field(r'!@#№$;:%^&?*(){}[]\/<>+=~`\' ', description="Bad characters to replace")
+    skip_existing: bool = Field(False, description="Skip existing files")
+    output_template: str = Field("%an-%tn.%ext", description="Output filename template")
+
+    # Metadata options
+    album: Optional[str] = Field(None, description="Album name")
+    comment: Optional[str] = Field(None, description="Comment")
+    no_comment: bool = Field(False, description="Ignore comment")
+    comment_stream: Optional[int] = Field(None, description="Comment stream index")
+    merge_comments: bool = Field(False, description="Merge all comments")
+    comment_separator: str = Field("; ", description="Separator for merged comments")

web/backend/services/splitter.py

@@ -40,9 +40,13 @@ def run_split_task(task_id: str, tracklist: List[TracklistEntry], options: Dict[
 
         from types import SimpleNamespace
 
+        # Build args namespace using the new fields
         args = SimpleNamespace(
-            format=options.get("format", "mp3"),
-            transcode_to=options.get("transcode_to", None),
+            container=options.get("container"),  # None -> auto-detect
+            audio_codec=options.get("audio_codec", "copy"),
+            video_codec=options.get("video_codec", "copy"),
+            subtitle_codec=options.get("subtitle_codec", "copy"),
+            video_quality=options.get("video_quality"),
             drop_video=options.get("drop_video", False),
             drop_subs=options.get("drop_subs", False),
             number_tracks=options.get("number_tracks", False),
@@ -66,17 +70,18 @@ def run_split_task(task_id: str, tracklist: List[TracklistEntry], options: Dict[
 
         from audio_splitter.core import split_audio
 
+        # Cover image handling is now done internally by split_audio()
+        # via the handler system (opustags for Opus, ffmpeg for others)
+        args.cover_image = None
+
         task_manager.update_task_with_progress(
             task_id, progress=10, message="Starting split..."
         )
 
-        # Run the split
         split_audio(str(input_path), str(output_dir), tracks, args)
 
-        # Get output files
         output_files = FileManager.get_output_files(task_id)
 
-        # Final status update
         task_manager.update_task_with_progress(
             task_id,
             progress=100,
@@ -84,13 +89,11 @@ def run_split_task(task_id: str, tracklist: List[TracklistEntry], options: Dict[
             status=TaskStatus.DONE
         )
 
-        # Add tracks to the task state
         task_manager.update_task(
             task_id,
             tracks=output_files
         )
 
-        # Give WebSocket time to send the final message
         time.sleep(0.5)
 
     except Exception as e:

web/frontend/Dockerfile

@@ -1,27 +1,42 @@
-# Stage 1: Build
+# web/frontend/Dockerfile
+# Build context must be the project root.
+
 FROM node:20-alpine AS builder
 
+# Install Python for the generation script
+RUN apk add --no-cache python3 py3-pip
+
 WORKDIR /app
 
-# Install dependencies
-COPY package.json package-lock.json* ./
+# Copy frontend package files and install dependencies
+COPY web/frontend/package.json web/frontend/package-lock.json* ./
 RUN npm install
 
-# Copy the application code and build
-COPY . .
+# Copy the frontend source code
+COPY web/frontend/ .
+
+# Copy the Python defaults and the generation script into the expected location
+# The generate script in package.json expects ../../scripts/generate_ts_defaults.py
+# So we must place it at /app/../../scripts/ which is /scripts/
+# But we can't COPY to a parent directory. Instead, we'll copy to /app/scripts/
+# and adjust the package.json script to use ./scripts/generate_ts_defaults.py
+# Actually, the simplest fix is to copy to /app/scripts/ and then adjust package.json.
+#
+# Let's use a different approach: copy to /app/scripts/ and update the generate script.
+COPY audio_splitter/defaults.py /app/scripts/defaults.py
+COPY scripts/generate_ts_defaults.py /app/scripts/generate_ts_defaults.py
+
+# Run the generation script
+RUN python /app/scripts/generate_ts_defaults.py
+
+# Build the frontend
 RUN npm run build
 
 # Stage 2: Production (nginx)
 FROM nginx:alpine
 
-# Copy built assets from builder
 COPY --from=builder /app/dist /usr/share/nginx/html
+COPY web/frontend/nginx/nginx.conf /etc/nginx/conf.d/default.conf
 
-# Copy nginx configuration
-COPY nginx/nginx.conf /etc/nginx/conf.d/default.conf
-
-# Expose the port
 EXPOSE 80
-
-# Start nginx
 CMD ["nginx", "-g", "daemon off;"]

web/frontend/package.json

@@ -4,6 +4,9 @@
   "version": "0.1.0",
   "type": "module",
   "scripts": {
+    "generate": "python scripts/generate_ts_defaults.py",
+    "predev": "npm run generate",
+    "prebuild": "npm run generate",
     "dev": "vite",
     "build": "tsc && vite build",
     "lint": "eslint . --ext ts,tsx --report-unused-disable-directives --max-warnings 0",

web/frontend/src/App.tsx

@@ -68,16 +68,15 @@ const App: React.FC = () => {
     reset()
   }
 
-  const isSplitDisabled = !taskId || !isValid || entries.length === 0 || isProcessing || !!formatError
+  const isSplitDisabled =
+    !taskId ||
+    !isValid ||
+    entries.length === 0 ||
+    isProcessing ||
+    !!formatError
 
   return (
-    <ThemeProvider
-      theme={createTheme({
-        palette: {
-          mode: theme,
-        },
-      })}
-    >
+    <ThemeProvider theme={createTheme({ palette: { mode: theme } })}>
       <CssBaseline />
       <Layout>
         <Grid container spacing={3}>

web/frontend/src/api/client.ts

@@ -1,5 +1,12 @@
 import axios from 'axios'
-import { TracklistEntry, SplitOptions, TaskStatus } from '../types'
+import {
+  TracklistEntry,
+  SplitOptions,
+  TaskStatus,
+  FormatsResponse,
+  UploadResponse,
+  SplitResponse,
+} from '../types'
 
 export const api = axios.create({
   baseURL: '/api',
@@ -8,16 +15,14 @@ export const api = axios.create({
   },
 })
 
-export const uploadFile = async (file: File): Promise<{ task_id: string; filename: string; size: number }> => {
+export const uploadFile = async (file: File): Promise<UploadResponse> => {
   const formData = new FormData()
   formData.append('file', file)
-
   const response = await api.post('/upload', formData, {
     headers: {
       'Content-Type': 'multipart/form-data',
     },
   })
-
   return response.data
 }
 
@@ -25,12 +30,32 @@ export const startSplit = async (
   task_id: string,
   tracklist: TracklistEntry[],
   options: SplitOptions
-): Promise<{ task_id: string; status: string }> => {
-  const response = await api.post('/split', {
+): Promise<SplitResponse> => {
+  // Build request payload (only send fields that are not undefined)
+  const payload: any = {
     task_id,
     tracklist,
-    options,
-  })
+    container: options.container, // null means auto-detect
+    audio_codec: options.audio_codec,
+    video_codec: options.video_codec,
+    subtitle_codec: options.subtitle_codec,
+    video_quality: options.video_quality,
+    drop_video: options.drop_video,
+    drop_subs: options.drop_subs,
+    number_tracks: options.number_tracks,
+    replace_bad_chars: options.replace_bad_chars,
+    replacement_char: options.replacement_char,
+    bad_chars: options.bad_chars,
+    skip_existing: options.skip_existing,
+    output_template: options.output_template,
+    album: options.album || null,
+    comment: options.comment || null,
+    no_comment: options.no_comment,
+    comment_stream: options.comment_stream,
+    merge_comments: options.merge_comments,
+    comment_separator: options.comment_separator,
+  }
+  const response = await api.post('/split', payload)
   return response.data
 }
 
@@ -47,8 +72,7 @@ export const getDownloadZipUrl = (task_id: string): string => {
   return `/api/download/${task_id}/splits.zip`
 }
 
-// New functions for format validation feature
-export const getFormatInfo = async (): Promise<{ formats: Array<{ name: string; audio_only: boolean }> }> => {
+export const getFormats = async (): Promise<FormatsResponse> => {
   const response = await api.get('/formats')
   return response.data
 }
@@ -63,3 +87,8 @@ export const getTaskInfo = async (task_id: string): Promise<{
   const response = await api.get(`/info/${task_id}`)
   return response.data
 }
+
+export const getRecommendedFormat = async (task_id: string): Promise<{ format: string }> => {
+  const response = await api.get(`/info/recommended-format/${task_id}`)
+  return response.data
+}

web/frontend/src/components/OptionsPanel.tsx

@@ -1,4 +1,4 @@
-import React, { useEffect } from 'react'
+import React, { useEffect, useMemo } from 'react'
 import {
   Box,
   Paper,
@@ -16,7 +16,14 @@ import { ExpandMore, ExpandLess } from '@mui/icons-material'
 import { useOptionsStore } from '../stores/optionsStore'
 import { useUploadStore } from '../stores/uploadStore'
 import { useValidationStore } from '../stores/validationStore'
+import { getFormats } from '../api/client'
+import { SplitOptions } from '../types'
+import { useFilterCodecs } from '../hooks/useFilterCodecs'
+import { useFormatValidation } from '../hooks/useFormatValidation'
 
+// ------------------------------------------------------------------------------
+// Section component (collapsible)
+// ------------------------------------------------------------------------------
 interface SectionProps {
   title: string
   children: React.ReactNode
@@ -25,7 +32,6 @@ interface SectionProps {
 
 const Section: React.FC<SectionProps> = ({ title, children, defaultExpanded = false }) => {
   const [expanded, setExpanded] = React.useState(defaultExpanded)
-
   return (
     <Box sx={{ mb: 2 }}>
       <Box
@@ -51,54 +57,64 @@ const Section: React.FC<SectionProps> = ({ title, children, defaultExpanded = fa
   )
 }
 
+// ------------------------------------------------------------------------------
+// Main OptionsPanel
+// ------------------------------------------------------------------------------
 export const OptionsPanel: React.FC = () => {
-  const { options, setOptions } = useOptionsStore()
+  const {
+    options,
+    setOptions,
+    containers,
+    codecs,
+    compatibility,
+    setContainers,
+    setCodecs,
+    setCompatibility,
+  } = useOptionsStore()
+
   const { hasVideo } = useUploadStore()
   const { formatError, setFormatError } = useValidationStore()
 
-  // Audio-only formats from backend constants (hardcoded for now)
-  const audioOnlyFormats = ['mp3', 'm4a', 'ogg', 'opus', 'flac', 'wav', 'aac']
-
-  const handleFormatChange = (e: React.ChangeEvent<HTMLInputElement>) => {
-    const newFormat = e.target.value
-    setOptions({ format: newFormat })
-
-    // Validate format
-    if (audioOnlyFormats.includes(newFormat) && hasVideo && !options.drop_video) {
-      setFormatError(
-        `Format '${newFormat}' does not support video streams. Please enable "Drop video" or choose a container that supports video (e.g., MKV, MP4).`
-      )
-    } else {
-      setFormatError(null)
-    }
-  }
-
-  const handleDropVideoChange = (e: React.ChangeEvent<HTMLInputElement>) => {
-    const checked = e.target.checked
-    setOptions({ drop_video: checked })
-    // Re-validate format
-    if (audioOnlyFormats.includes(options.format) && hasVideo && !checked) {
-      setFormatError(
-        `Format '${options.format}' does not support video streams. Please enable "Drop video" or choose a container that supports video (e.g., MKV, MP4).`
-      )
-    } else {
-      setFormatError(null)
-    }
-  }
-
-  // Re-validate when hasVideo changes (e.g., after upload)
+  // Fetch formats on mount
   useEffect(() => {
-    const shouldShowError = audioOnlyFormats.includes(options.format) && hasVideo && !options.drop_video
-    const newError = shouldShowError
-      ? `Format '${options.format}' does not support video streams. Please enable "Drop video" or choose a container that supports video (e.g., MKV, MP4).`
-      : null
-
-    // Only update if the error state actually changes
-    if (newError !== formatError) {
-      setFormatError(newError)
+    const fetchFormats = async () => {
+      try {
+        const data = await getFormats()
+        setContainers(data.containers || [])
+        setCodecs(data.codecs || [])
+        setCompatibility(data.compatibility || {})
+      } catch (err) {
+        console.error('Failed to fetch formats:', err)
       }
-  }, [hasVideo, options.format, options.drop_video, formatError, setFormatError])
+    }
+    fetchFormats()
+  }, [setContainers, setCodecs, setCompatibility])
 
+  // --------------------------------------------------------------
+  // Filter codec options based on selected container
+  // --------------------------------------------------------------
+  const { filteredAudioCodecs, filteredVideoCodecs } = useFilterCodecs(compatibility, options.container, codecs)
+
+  // --------------------------------------------------------------
+  // Validate compatibility
+  // --------------------------------------------------------------
+  useFormatValidation(options, hasVideo, compatibility, containers, setFormatError)
+
+  // --------------------------------------------------------------
+  // Handlers
+  // --------------------------------------------------------------
+  const handleChange = (field: keyof SplitOptions, value: any) => {
+    setOptions({ [field]: value })
+  }
+
+  const handleContainerChange = (e: React.ChangeEvent<HTMLInputElement>) => {
+    const value = e.target.value === '' ? null : e.target.value
+    handleChange('container', value)
+  }
+
+  // --------------------------------------------------------------
+  // Render
+  // --------------------------------------------------------------
   return (
     <Paper sx={{ p: 3 }}>
       <Typography variant="h6" sx={{ mb: 2 }}>
@@ -111,55 +127,101 @@ export const OptionsPanel: React.FC = () => {
         </Alert>
       )}
 
-      {/* Output Settings */}
+      {/* ------------------------------------------------------------------------
+          Output Settings
+      ------------------------------------------------------------------------ */}
       <Section title="Output Settings" defaultExpanded>
         <Box sx={{ display: 'flex', flexDirection: 'column', gap: 2 }}>
+          {/* Container dropdown */}
           <TextField
-            label="Format"
+            label="Container"
             select
-            value={options.format}
-            onChange={handleFormatChange}
+            value={options.container ?? ''}
+            onChange={handleContainerChange}
             fullWidth
             size="small"
             error={!!formatError}
+            helperText={
+              formatError || "Select a container (auto-detect if empty)."
+            }
           >
-            <MenuItem value="mp3">MP3</MenuItem>
-            <MenuItem value="m4a">M4A</MenuItem>
-            <MenuItem value="mkv">MKV</MenuItem>
-            <MenuItem value="mp4">MP4</MenuItem>
-            <MenuItem value="ogg">OGG</MenuItem>
-            <MenuItem value="opus">OPUS</MenuItem>
-            <MenuItem value="flac">FLAC</MenuItem>
-            <MenuItem value="wav">WAV</MenuItem>
-            <MenuItem value="aac">AAC</MenuItem>
+            <MenuItem value="">Auto-detect</MenuItem>
+            {containers.map((c) => (
+              <MenuItem key={c.name} value={c.name}>
+                {c.name.toUpperCase()} ({c.extension})
+              </MenuItem>
+            ))}
           </TextField>
 
+          {/* Audio Codec dropdown */}
           <TextField
-            label="Transcode to"
+            label="Audio Codec"
             select
-            value={options.transcode_to || ''}
-            onChange={(e) => handleChange('transcode_to', e.target.value || undefined)}
+            value={options.audio_codec}
+            onChange={(e) => handleChange('audio_codec', e.target.value)}
             fullWidth
             size="small"
+            helperText="Audio codec (copy = keep original)"
           >
-            <MenuItem value="">Copy (no transcoding)</MenuItem>
-            <MenuItem value="libmp3lame">MP3 (LAME)</MenuItem>
-            <MenuItem value="aac">AAC</MenuItem>
-            <MenuItem value="libopus">OPUS</MenuItem>
+            <MenuItem value="copy">Copy (original)</MenuItem>
+            {filteredAudioCodecs.map((c) => (
+              <MenuItem key={c.name} value={c.name}>
+                {c.name.toUpperCase()}
+              </MenuItem>
+            ))}
           </TextField>
 
+          {/* Video Codec dropdown */}
+          <TextField
+            label="Video Codec"
+            select
+            value={options.video_codec}
+            onChange={(e) => handleChange('video_codec', e.target.value)}
+            fullWidth
+            size="small"
+            helperText="Video codec (copy = keep original)"
+            disabled={!hasVideo || options.drop_video}
+          >
+            <MenuItem value="copy">Copy (original)</MenuItem>
+            {filteredVideoCodecs.map((c) => (
+              <MenuItem key={c.name} value={c.name}>
+                {c.name.toUpperCase()}
+              </MenuItem>
+            ))}
+          </TextField>
+
+          {/* Video Quality */}
+          <TextField
+            label="Video Quality"
+            type="number"
+            value={options.video_quality ?? ''}
+            onChange={(e) => {
+              const val = e.target.value === '' ? null : parseInt(e.target.value, 10)
+              handleChange('video_quality', val)
+            }}
+            fullWidth
+            size="small"
+            disabled={!hasVideo || options.drop_video}
+            helperText="Optional quality value (encoder-specific; e.g., 1-31 for libx264, 0-10 for Theora)"
+            InputProps={{
+              inputProps: { min: 0, max: 51, step: 1 },
+            }}
+          />
+
+          {/* Drop video (if video present) */}
           {hasVideo && (
             <FormControlLabel
               control={
                 <Switch
                   checked={options.drop_video}
-                  onChange={handleDropVideoChange}
+                  onChange={(e) => handleChange('drop_video', e.target.checked)}
                 />
               }
               label="Drop video streams"
             />
           )}
 
+          {/* Drop subtitles */}
           <FormControlLabel
             control={
               <Switch
@@ -172,7 +234,9 @@ export const OptionsPanel: React.FC = () => {
         </Box>
       </Section>
 
-      {/* Filename Settings */}
+      {/* ------------------------------------------------------------------------
+          Filename Settings
+      ------------------------------------------------------------------------ */}
       <Section title="Filename Settings">
         <Box sx={{ display: 'flex', flexDirection: 'column', gap: 2 }}>
           <TextField
@@ -228,7 +292,9 @@ export const OptionsPanel: React.FC = () => {
         </Box>
       </Section>
 
-      {/* Metadata Settings */}
+      {/* ------------------------------------------------------------------------
+          Metadata Settings
+      ------------------------------------------------------------------------ */}
       <Section title="Metadata Settings">
         <Box sx={{ display: 'flex', flexDirection: 'column', gap: 2 }}>
           <TextField
@@ -259,7 +325,7 @@ export const OptionsPanel: React.FC = () => {
             type="number"
             value={options.comment_stream ?? ''}
             onChange={(e) =>
-              handleChange('comment_stream', e.target.value === '' ? null : parseInt(e.target.value))
+              handleChange('comment_stream', e.target.value === '' ? null : parseInt(e.target.value, 10))
             }
             size="small"
             disabled={options.no_comment}
@@ -284,7 +350,9 @@ export const OptionsPanel: React.FC = () => {
         </Box>
       </Section>
 
-      {/* Tracklist Settings */}
+      {/* ------------------------------------------------------------------------
+          Tracklist Settings
+      ------------------------------------------------------------------------ */}
       <Section title="Tracklist Settings" defaultExpanded>
         <Box sx={{ display: 'flex', flexDirection: 'column', gap: 2 }}>
           <TextField
@@ -299,9 +367,4 @@ export const OptionsPanel: React.FC = () => {
       </Section>
     </Paper>
   )
-
-  // Helper function for option updates
-  function handleChange(field: string, value: any) {
-    setOptions({ [field]: value })
-  }
 }

web/frontend/src/components/TracklistEditor.tsx

@@ -1,4 +1,4 @@
-import React, { useCallback, useEffect, useState } from 'react'
+import React, { useCallback, useEffect, useRef, useState } from 'react'
 import { Box, Paper, TextField, Typography, Alert } from '@mui/material'
 import { useDropzone } from 'react-dropzone'
 import { useTracklistStore } from '../stores/tracklistStore'
@@ -10,6 +10,9 @@ export const TracklistEditor: React.FC = () => {
   const { options } = useOptionsStore()
   const [isDragging, setIsDragging] = useState(false)
 
+  const textAreaRef = useRef<HTMLTextAreaElement>(null)
+  const lineNumbersRef = useRef<HTMLDivElement>(null)
+
   const validate = (text: string) => {
     const result = parseAndValidateTracklist(text, options.tracklist_format)
     setEntries(result.entries)
@@ -23,10 +26,29 @@ export const TracklistEditor: React.FC = () => {
     validate(text)
   }
 
+  const handleScroll = useCallback(() => {
+    if (lineNumbersRef.current && textAreaRef.current) {
+      lineNumbersRef.current.scrollTop = textAreaRef.current.scrollTop
+    }
+  }, [])
+
+  useEffect(() => {
+    const textArea = textAreaRef.current
+    if (textArea) {
+      textArea.addEventListener('scroll', handleScroll)
+      return () => textArea.removeEventListener('scroll', handleScroll)
+    }
+  }, [handleScroll])
+
+  useEffect(() => {
+    if (rawText) {
+      validate(rawText)
+    }
+  }, [options.tracklist_format])
+
   const onDrop = useCallback(
     (acceptedFiles: File[]) => {
       if (acceptedFiles.length === 0) return
-
       const file = acceptedFiles[0]
       const reader = new FileReader()
       reader.onload = (event) => {
@@ -48,13 +70,6 @@ export const TracklistEditor: React.FC = () => {
     multiple: false,
   })
 
-  // Re-validate when tracklist format changes
-  useEffect(() => {
-    if (rawText) {
-      validate(rawText)
-    }
-  }, [options.tracklist_format])
-
   const lineCount = rawText.split('\n').filter(line => line.trim() !== '').length
 
   return (
@@ -82,12 +97,13 @@ export const TracklistEditor: React.FC = () => {
         </Typography>
       </Typography>
 
-      <Box sx={{ display: 'flex', gap: 2 }}>
+      <Box sx={{ display: 'flex', gap: 2, position: 'relative' }}>
         {/* Line numbers column */}
         <Box
+          ref={lineNumbersRef}
           sx={{
             minWidth: 40,
-            maxWidth: 40,
+            maxWidth: 60,  // Allow more space for 3-digit numbers
             fontFamily: 'monospace',
             fontSize: '14px',
             lineHeight: 1.7,
@@ -95,6 +111,11 @@ export const TracklistEditor: React.FC = () => {
             textAlign: 'right',
             userSelect: 'none',
             overflow: 'hidden',
+            paddingTop: '8.5px',
+            paddingBottom: '8.5px',
+            scrollbarWidth: 'none',
+            '&::-webkit-scrollbar': { display: 'none' },
+            whiteSpace: 'nowrap',  // Prevent wrapping of line numbers
           }}
         >
           {rawText.split('\n').map((_, i) => (
@@ -102,7 +123,7 @@ export const TracklistEditor: React.FC = () => {
           ))}
         </Box>
 
-        {/* Editor text area */}
+        {/* Editor text area – now with horizontal scroll and no wrap */}
         <TextField
           multiline
           fullWidth
@@ -112,11 +133,19 @@ export const TracklistEditor: React.FC = () => {
           onChange={handleTextChange}
           placeholder={`Enter your tracklist here...\n\nExample (format: ${options.tracklist_format}):\n00:00 Intro\n01:30 Song One - Artist A\n04:20-06:45 Another Song - Artist B`}
           variant="outlined"
+          inputRef={textAreaRef}
           sx={{
             '& .MuiInputBase-root': {
               fontFamily: 'monospace',
               fontSize: '14px',
               lineHeight: 1.7,
+              overflowX: 'auto',  // Enable horizontal scroll
+            },
+            '& .MuiInputBase-input': {
+              paddingTop: '8.5px',
+              paddingBottom: '8.5px',
+              whiteSpace: 'nowrap',  // Prevent wrapping
+              overflowX: 'auto',
             },
           }}
           error={!isValid && errors.length > 0}

web/frontend/src/components/UploadZone.tsx

@@ -3,7 +3,8 @@ import { useDropzone } from 'react-dropzone'
 import { Box, Typography, Paper, LinearProgress, Alert } from '@mui/material'
 import { CloudUpload, InsertDriveFile } from '@mui/icons-material'
 import { useUploadStore } from '../stores/uploadStore'
-import { uploadFile, getTaskInfo } from '../api/client'
+import { useOptionsStore } from '../stores/optionsStore'  // NEW
+import { uploadFile, getTaskInfo, getRecommendedFormat } from '../api/client'  // NEW
 import { useTaskStore } from '../stores/taskStore'
 
 const ALLOWED_EXTENSIONS = ['.mp3', '.flac', '.wav', '.m4a', '.ogg', '.opus', '.aac', '.wma', '.aiff', '.alac', '.ac3']
@@ -30,6 +31,7 @@ export const UploadZone: React.FC = () => {
   } = useUploadStore()
 
   const { setTaskId: setTaskIdStore } = useTaskStore()
+  const { setOptions } = useOptionsStore()   // NEW
 
   const onDrop = useCallback(
     async (acceptedFiles: File[]) => {
@@ -65,9 +67,19 @@ export const UploadZone: React.FC = () => {
           setHasAudio(info.has_audio)
           setHasSubtitle(info.has_subtitle)
           setAudioCodec(info.audio_codec)
+
+          // Fetch recommended format and update options
+          try {
+            // Inside UploadZone.tsx, after fetching recommended format:
+            const rec = await getRecommendedFormat(taskId)
+            // Update options store with container (not format)
+            setOptions({ container: rec.format })
+          } catch (err) {
+            console.warn('Failed to fetch recommended format, using default', err)
+          }
         } catch (err) {
           console.error('Failed to fetch stream info:', err)
-          // Don't block the upload flow if this fails; we'll just assume no video
+          // Don't block upload flow; user can manually change options
         }
       } catch (err: any) {
         setError(err.response?.data?.detail || err.message || 'Upload failed')
@@ -78,7 +90,7 @@ export const UploadZone: React.FC = () => {
         setFileSize(0)
       }
     },
-    [setFile, setFileName, setFileSize, setIsUploading, setUploadProgress, setError, setTaskId, setTaskIdStore]
+    [setFile, setFileName, setFileSize, setIsUploading, setUploadProgress, setError, setTaskId, setTaskIdStore, setHasVideo, setHasAudio, setHasSubtitle, setAudioCodec, setOptions]
   )
 
   const { getRootProps, getInputProps, isDragActive } = useDropzone({

web/frontend/src/hooks/useFilterCodecs.ts

@@ -0,0 +1,31 @@
+import { useMemo } from 'react'
+import { CodecInfo } from '../types'
+
+export interface CompatibilityEntry {
+  audio: string[] | null
+  video: string[] | null
+}
+
+export function useFilterCodecs(
+  compatibility: Record<string, CompatibilityEntry>,
+  container: string | null,
+  codecs: CodecInfo[]
+) {
+  const filteredAudioCodecs = useMemo(() => {
+    const entry = compatibility?.[container || '']
+    if (!entry) return codecs.filter(c => c.codec_type === 'audio')
+    const audioList = entry.audio
+    if (audioList === null) return codecs.filter(c => c.codec_type === 'audio')
+    return codecs.filter(c => c.codec_type === 'audio' && audioList.includes(c.name))
+  }, [compatibility, container, codecs])
+
+  const filteredVideoCodecs = useMemo(() => {
+    const entry = compatibility?.[container || '']
+    if (!entry) return codecs.filter(c => c.codec_type === 'video')
+    const videoList = entry.video
+    if (videoList === null) return codecs.filter(c => c.codec_type === 'video')
+    return codecs.filter(c => c.codec_type === 'video' && videoList.includes(c.name))
+  }, [compatibility, container, codecs])
+
+  return { filteredAudioCodecs, filteredVideoCodecs }
+}

web/frontend/src/hooks/useFormatValidation.ts

@@ -0,0 +1,56 @@
+import { useEffect } from 'react'
+import { ContainerInfo } from '../types'
+import { CompatibilityEntry } from './useFilterCodecs'
+
+export function useFormatValidation(
+  options: {
+    container: string | null
+    audio_codec: string
+    video_codec: string
+    drop_video: boolean
+  },
+  hasVideo: boolean,
+  compatibility: Record<string, CompatibilityEntry>,
+  containers: ContainerInfo[],
+  setFormatError: (error: string | null) => void
+) {
+  useEffect(() => {
+    const selectedContainer = containers.find(c => c.name === options.container)
+    if (!selectedContainer?.supports_video && hasVideo && !options.drop_video) {
+      setFormatError(
+        `Container '${options.container}' does not support video streams. Please enable "Drop video" or choose a container that supports video.`
+      )
+      return
+    }
+
+    // Check audio codec compatibility
+    if (options.audio_codec && options.audio_codec !== 'copy' && options.container) {
+      const entry = compatibility?.[options.container]
+      if (entry) {
+        const audioList = entry.audio
+        if (audioList !== null && !audioList.includes(options.audio_codec)) {
+          setFormatError(
+            `Audio codec '${options.audio_codec}' is not supported by container '${options.container}'.`
+          )
+          return
+        }
+      }
+    }
+
+    // Check video codec compatibility
+    if (options.video_codec && options.video_codec !== 'copy' && options.container && hasVideo && !options.drop_video) {
+      const entry = compatibility?.[options.container]
+      if (entry) {
+        const videoList = entry.video
+        if (videoList !== null && !videoList.includes(options.video_codec)) {
+          setFormatError(
+            `Video codec '${options.video_codec}' is not supported by container '${options.container}'.`
+          )
+          return
+        }
+      }
+    }
+
+    setFormatError(null)
+  }, [options.container, options.audio_codec, options.video_codec, options.drop_video, hasVideo, compatibility, containers, setFormatError])
+}

web/frontend/src/stores/optionsStore.ts

@@ -1,37 +1,77 @@
 import { create } from 'zustand'
-import { SplitOptions } from '../types'
+import { SplitOptions, ContainerInfo, CodecInfo } from '../types'
+import {
+  DEFAULT_FORMAT,
+  DEFAULT_OUTPUT_TEMPLATE,
+  DEFAULT_REPLACEMENT_CHAR,
+  DEFAULT_BAD_CHARS,
+  DEFAULT_ALBUM,
+  DEFAULT_COMMENT,
+  DEFAULT_NO_COMMENT,
+  DEFAULT_COMMENT_STREAM,
+  DEFAULT_MERGE_COMMENTS,
+  DEFAULT_COMMENT_SEPARATOR,
+  DEFAULT_DROP_VIDEO,
+  DEFAULT_DROP_SUBS,
+  DEFAULT_NUMBER_TRACKS,
+  DEFAULT_REPLACE_BAD_CHARS,
+  DEFAULT_SKIP_EXISTING,
+  DEFAULT_TRACKLIST_FORMAT,
+} from '../constants/generated'
 
+// We use DEFAULT_FORMAT only as a fallback; container default is null (auto-detect)
 const DEFAULT_OPTIONS: SplitOptions = {
-  format: 'mp3',
-  transcode_to: '',
-  drop_video: false,
-  drop_subs: false,
-  number_tracks: false,
-  replace_bad_chars: false,
-  replacement_char: '_',
-  bad_chars: '!@#№$;:%^&?*(){}[]\\/<>+=~`\' ',
-  skip_existing: false,
-  output_template: '%an-%tn.%ext',
-  album: '',
-  comment: '',
-  no_comment: false,
-  comment_stream: null,
-  merge_comments: false,
-  comment_separator: '; ',
-  tracklist_format: '%ts %tn - %an', // NEW
+  container: null,
+  audio_codec: 'copy',
+  video_codec: 'copy',
+  subtitle_codec: 'copy',
+  video_quality: null,
+  drop_video: DEFAULT_DROP_VIDEO,
+  drop_subs: DEFAULT_DROP_SUBS,
+  number_tracks: DEFAULT_NUMBER_TRACKS,
+  replace_bad_chars: DEFAULT_REPLACE_BAD_CHARS,
+  replacement_char: DEFAULT_REPLACEMENT_CHAR,
+  bad_chars: DEFAULT_BAD_CHARS,
+  skip_existing: DEFAULT_SKIP_EXISTING,
+  output_template: DEFAULT_OUTPUT_TEMPLATE,
+  album: DEFAULT_ALBUM ?? '',
+  comment: DEFAULT_COMMENT ?? '',
+  no_comment: DEFAULT_NO_COMMENT,
+  comment_stream: DEFAULT_COMMENT_STREAM,
+  merge_comments: DEFAULT_MERGE_COMMENTS,
+  comment_separator: DEFAULT_COMMENT_SEPARATOR,
+  tracklist_format: DEFAULT_TRACKLIST_FORMAT,
 }
 
 interface OptionsState {
   options: SplitOptions
-  setOptions: (options: Partial<SplitOptions>) => void
+  containers: ContainerInfo[]
+  codecs: CodecInfo[]
+  compatibility: Record<string, { audio: string[] | null; video: string[] | null }>
+  setOptions: (newOptions: Partial<SplitOptions>) => void
+  setContainers: (containers: ContainerInfo[]) => void
+  setCodecs: (codecs: CodecInfo[]) => void
+  setCompatibility: (compat: Record<string, { audio: string[] | null; video: string[] | null }>) => void
   reset: () => void
 }
 
 export const useOptionsStore = create<OptionsState>((set) => ({
   options: { ...DEFAULT_OPTIONS },
+  containers: [],
+  codecs: [],
+  compatibility: {},
   setOptions: (newOptions) =>
     set((state) => ({
       options: { ...state.options, ...newOptions },
     })),
-  reset: () => set({ options: { ...DEFAULT_OPTIONS } }),
+  setContainers: (containers) => set({ containers }),
+  setCodecs: (codecs) => set({ codecs }),
+  setCompatibility: (compatibility) => set({ compatibility }),
+  reset: () =>
+    set({
+      options: { ...DEFAULT_OPTIONS },
+      containers: [],
+      codecs: [],
+      compatibility: {},
+    }),
 }))

web/frontend/src/types/index.ts

@@ -22,8 +22,11 @@ export interface TaskStatus {
 }
 
 export interface SplitOptions {
-  format: string
-  transcode_to?: string
+  container: string | null          // null = auto-detect
+  audio_codec: string               // 'copy' or encoder name
+  video_codec: string               // 'copy' or encoder name
+  subtitle_codec: string            // 'copy' or encoder name
+  video_quality: number | null      // encoder-specific integer
   drop_video: boolean
   drop_subs: boolean
   number_tracks: boolean
@@ -38,7 +41,34 @@ export interface SplitOptions {
   comment_stream: number | null
   merge_comments: boolean
   comment_separator: string
-  tracklist_format: string
+  tracklist_format: string          // for frontend parsing
+}
+
+export interface ContainerInfo {
+  name: string
+  ffmpeg: string
+  extension: string
+  supports_video: boolean
+  supports_subs: boolean
+}
+
+export interface CodecInfo {
+  name: string
+  ffmpeg: string
+  recommended_container: string
+  recommended_extension: string
+  codec_type: 'audio' | 'video' | 'subtitle'
+}
+
+export interface CompatibilityEntry {
+  audio: string[] | null
+  video: string[] | null
+}
+
+export interface FormatsResponse {
+  containers: ContainerInfo[]
+  codecs: CodecInfo[]
+  compatibility: Record<string, CompatibilityEntry>
 }
 
 export interface UploadResponse {